US 7,916,971 B2Grant
Image processing method and apparatus
Issue Date:2011-03-29
•110 Claims
•5 Drawing Sheets
Abstract
An image processing technique includes acquiring a main image of a scene and determining one or more facial regions in the main image. The facial regions are analysed to determine if any of the facial regions includes a defect. A sequence of relatively low resolution images nominally of the same scene is also acquired. One or more sets of low resolution facial regions in the sequence of low resolution images are determined and analysed for defects. Defect free facial regions of a set are combined to provide a high quality defect free facial region. At least a portion of any defective facial regions of the main image are corrected with image information from a corresponding high quality defect free facial region.
Metadata
Assignee
- Tessera Technologies Ireland Limited
Inventors
- Petronel Bigioi
- Peter Corcoran
- Eran Steinberg
Application Information
Application Number:US 11/752,925
Filing Date:2007-05-24
Priority Date:2007-05-24
Art Unit:2624
Classifications
IPC:
G06K9/40
Patent Drawings (5 sheets)
Description
Background
[0001] The present invention relates to an image processing method and apparatus. One of the most common reasons for an acquired digital photograph to be discarded or spoiled is because one or more of the facial regions in the photograph suffer from photographic defects other than red-eye defects, even though red eye defects can be common in cameras not operating with the advantages of the techniques described, e.g., at U.S. Pat. No. 6,407,777, and at US published applications nos. 2005/0140801, 2005/0041121, 2006/0093212, and 2006/0204054, which are assigned to the same assignee and hereby incorporated by reference. Common examples occur when people move or shake their head; when someone closes their eyes or blinks or someone yawns. Where there are several faces in a photograph, it is sufficient for one face to be “defective” for the whole shot to be spoiled. Although digital cameras allow users to quickly shoot several pictures of the same scene. Typically, such cameras do not provide warnings of facial errors, nor provide a way to correct for such errors without repeating the composition stages (i.e. getting everyone together again in a group) of taking the photograph and re-shooting the scene. This type of problem is particularly difficult with children who are often photographed in unusual spontaneous poses which cannot be duplicated. When such a shot is spoiled because the child moved their head at the moment of acquisition, it is very disappointing for the photographer.
[0002] U.S. Pat. No. 6,301,440, which is incorporated by reference, discloses an image acquisition device wherein the instant of exposure is controlled by image content. When a trigger is activated, the image proposed by the user is analysed and imaging parameters are altered to obtain optimum image quality before the device proceeds to take the image. For example, the device could postpone acquisition of the image until every person in the image is smiling.
Summary of the Invention
[0003] An image processing method is provided including acquiring a main image of a scene. One or more facial regions are determined in the main image. The one or more main image facial regions are analyzed for defects and one or more are determined to be defective. A sequence of relatively low resolution images nominally of the scene are acquired. One or more sets of low resolution facial regions in the sequence are analyzed to determine one or more that correspond to a defective main image facial region. At least a portion of the defective main image facial region is corrected with image information from one or more corresponding low resolution facial regions not including a same defect as said portion of said defective main image facial region.
[0004] The sequence of low resolution images may be specifically acquired for a time period not including a time for acquiring the main image. The method may also include combining defect-free low resolution facial regions into a combined image, and correcting at least the portion of the defective main image facial region with image information from the combined image.
[0005] Another image processing method is provided that including acquiring a main image of a scene. One or more facial regions in the main image are determined, and analyzed to determine if any are defective. A sequence of relatively low resolution images is acquired nominally of the scene for a time period not including a time for acquiring the main image. One or more sets of low resolution facial regions are determined in the sequence of low resolution images. The sets of facial regions are analyzed to determine if any facial regions of a set corresponding to a defective facial region of the main image include a defect. Defect free facial regions of the corresponding set are combined to provide a high quality defect free facial region. At least a portion of any defective facial regions of said main image are corrected with image information from a corresponding high quality defect free facial region.
[0006] The time period may include one or more of a time period preceding or a time period following the time for acquiring the main image. The correcting may include applying a model including multiple vertices defining a periphery of a facial region to each high quality defect-free facial region and a corresponding defective facial region. Pixels may be mapped of the high quality defect-free facial region to the defective facial region according to the correspondence of vertices for the respective regions. The model may include an Active Appearance Model (AAM).
[0007] The main image may be acquired at an exposure level different to the exposure level of the low resolution images. The correcting may include mapping luminance levels of the high quality defect free facial region to luminance levels of the defective facial region.
[0008] Sets of low resolution facial regions from the sequence of low resolution images may be stored in an image header file of the main image.
[0009] The method may include displaying the main image and/or corrected image, and selected actions may be user-initiated.
[0010] The analyzing of the sets may include, prior to the combining in the second method, removing facial regions including faces exceeding an average size of faces in a set of facial regions by a threshold amount from said set of facial regions, and/or removing facial regions including faces with an orientation outside an average orientation of faces in a set of facial regions by a threshold amount from said set of facial regions.
[0011] The analyzing of sets may include the following:
-
- [0012] applying an Active Appearance Model (AAM) to each face of a set of facial regions;
- [0013] analyzing AAM parameters for each face of the set of facial regions to provide an indication of facial expression; and
- [0014] prior to the combining in the second method, removing faces having a defective expression from the set of facial regions.
[0015] The analyzing of sets may include the following:
-
- [0016] applying an Active Appearance Model (AAM) to each face of a set of facial regions;
- [0017] analysing AAM parameters for each face of the set of facial regions to provide an indication of facial orientation; and
- [0018] prior to said combining in the second method, removing faces having an undesirable orientation from said set of facial regions.
[0019] The analyzing of facial regions may include applying an Active Appearance Model (AAM) to each facial region, and analyzing AAM parameters for each facial region to provide an indication of facial expression, and/or analyzing each facial region for contrast, sharpness, texture, luminance levels or skin color or combinations thereof, and/or analyzing each facial region to determine if an eye of the facial region is closed, if a mouth of the facial region is open and/or if a mouth of the facial region is smiling.
[0020] The method may be such that the correcting, and the combining in the second method, only occur when the set of facial regions exceeds a given number. The method may also include resizing and aligning faces of the set of facial regions, and the aligning may be performed according to cardinal points of faces of the set of facial regions.
[0021] The correcting may include blending and/or infilling a corrected region of the main image with the remainder of the main image.
Brief Description of the Drawings
[0022] Embodiments will now be described, by way of example, with reference to the accompanying drawings, in which:
[0023] FIG. 1 is a block diagram of an image processing apparatus operating in accordance with an embodiment of the present invention;
[0024] FIG. 2 is a flow diagram of an image processing method according to a preferred embodiment of the present invention; and
[0025] FIGS. 3 and 4 show exemplary sets of images to which an active appearance model has been applied.
Detailed Description of the Preferred Embodiments
[0026] Certain embodiments can be implemented with a digital camera which incorporates (i) a face tracker operative on a preview image stream; (ii) a super-resolution processing module configured to create a higher resolution image from a composite of several low-resolution images; and (iii) a facial region quality analysis module for determining the quality of facial regions.
[0027] Preferably, super-resolution is applied to preview facial regions extracted during face tracking.
[0028] The embodiments enable the correction of errors or flaws in the facial regions of an acquired image within a digital camera using preview image data and employing super-resolution techniques.
[0029] FIG. 1 is a block diagram of an image acquisition device 20, which in the present embodiment is a portable digital camera, operating in accordance with certain embodiments. It will be appreciated that many of the processes implemented in the digital camera are implemented in or controlled by software operating on a microprocessor, central processing unit, controller, digital signal processor and/or an application specific integrated circuit, collectively depicted as processor 120. All user interface and control of peripheral components such as buttons and display is controlled by a microcontroller 122.
[0030] In operation, the processor 120, in response to a user input at 122, such as half pressing a shutter button (pre-capture mode 32), initiates and controls the digital photographic process. Ambient light exposure is determined using a light sensor 40 in order to automatically determine if a flash is to be used. The distance to the subject is determined using a focusing mechanism 50 which also focuses the image on an image capture device 60. If a flash is to be used, processor 120 causes a flash device 70 to generate a photographic flash in substantial coincidence with the recording of the image by the image capture device 60 upon full depression of the shutter button. The image capture device 60 digitally records the image in colour. The image capture device is known to those familiar with the art and may include a CCD (charge coupled device) or CMOS to facilitate digital recording. The flash may be selectively generated either in response to the light sensor 40 or a manual input 72 from the user of the camera. The high resolution image recorded by image capture device 60 is stored in an image store 80 which may comprise computer memory such a dynamic random access memory or a non-volatile memory. The camera is equipped with a display 100, such as an LCD, both for displaying preview images and displaying a user interface for camera control software.
[0031] In the case of preview images which are generated in the pre-capture mode 32 with the shutter button half-pressed, the display 100 can assist the user in composing the image, as well as being used to determine focusing and exposure. Temporary storage 82 is used to store one or plurality of the stream of preview images and can be part of the image store 80 or a separate component. The preview image is usually generated by the image capture device 60. For speed and memory efficiency reasons, preview images usually have a lower pixel resolution than the main image taken when the shutter button is fully depressed, and are generated by sub-sampling a raw captured image using software 124 which can be part of the general processor 120 or dedicated hardware or combination thereof.
[0032] In the present embodiment, a face detection and tracking module 130 such as described in U.S. application Ser. No. 11/464,083, filed Aug. 11, 2006, which is hereby incorporated by reference, is operably connected to the sub-sampler 124 to control the sub-sampled resolution of the preview images in accordance with the requirements of the face detection and tracking module. Preview images stored in temporary storage 82 are available to the module 130 which records the locations of faces tracked and detected in the preview image stream. In one embodiment, the module 130 is operably connected to the display 100 so that boundaries of detected and tracked face regions can be superimposed on the display around the faces during preview.
[0033] In the embodiment of FIG. 1 , the face tracking module 130 is arranged to extract and store tracked facial regions at relatively low resolution in a memory buffer such as memory 82 and possibly for storage as meta-data in an acquired image header stored in memory 80. Where multiple face regions are tracked, a buffer is established for each tracked face region. These buffers are of finite size (10-20 extracted face regions in a preferred embodiment) and generally operate on a first-in-first-out (FIFO) basis.
[0034] According to the preferred embodiment, the device 20 further comprises an image correction module 90. Where the module 90 is arranged for off-line correction of acquired images in an external processing device 10, such as a desktop computer, a colour printer or a photo kiosk, face regions detected and/or tracked in preview images are preferably stored as meta-data within the image header. However, where the module 90 is implemented within the camera 20, it can have direct access to the buffer 82 where preview images and/or face region information is stored.
[0035] In this embodiment, the module 90 receives the captured high resolution digital image from the store 80 and analyzes it to detect defects. The analysis is performed as described in the embodiments to follow. If defects are found, the module can modify the image to remove the defect. The modified image may be either displayed on image display 100, saved on a persistent storage 112 which can be internal or a removable storage such as CF card, SD card or the like, or downloaded to another device via image output means 110 which can be tethered or wireless. The module 90 can be brought into operation either automatically each time an image is captured, or upon user demand via input 30. Although illustrated as a separate item, where the module 90 is part of the camera, it may be implemented by suitable software on the processor 120.
[0036] The main components of the image correction module include a quality module 140 which is arranged to analyse face regions from either low or high resolution images to determine if these include face defects. A super-resolution module 160 is arranged to combine multiple low-resolution face regions of the same subject generally with the same pose and a desirable facial expression to provide a high quality face region for use in the correction process. In the present embodiment, an active appearance model (AAM) module 150 produces AAM parameters for face regions again from either low or high resolution images.
[0037] AAM modules are well known and a suitable module for the present embodiment is disclosed in “Fast and Reliable Active Appearance Model Search for 3-D Face Tracking”, F Dornaika and J Ahlberg, IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, Vol. 34, No. 4, pg 1838-1853, August 2004, although other models based on the original paper by TF Cootes et al “Active Appearance Models” Proc. European Conf. Computer Vision, 1998, pp 484-498 could also be employed.
[0038] The AAM module 150 can preferably cooperate with the quality module 140 to provide pose and/or expression indicators to allow for selection of images in the analysis and optionally in the correction process described below. Also, the AAM module 150 can preferably cooperate with the super-resolution module 160 to provide pose indicators to allow for selection of images in the correction process, again described in more detail below.
[0039] Referring now to FIG. 2 , which illustrates an exemplary processing flow for certain embodiments, when a main image is acquired, step 230, the location and size of any detected/tracked face region(s) in the main acquired image (high resolution) will be known by the module 90 from the module 130. Face detection can either be applied directly on the acquired image and/or information for face regions previously detected and/or tracked in the preview stream can be used for face detection in the main image (indicated by the dashed line extending from step 220). At step 250, the facial region quality analysis module 140 extracts and analyzes face regions tracked/detected at step 240 in the main image to determine the quality of the acquired face regions. For example, the module 140 can apply a preliminary analysis to measure the overall contrast, sharpness and/or texture of detected face region(s). This can indicate if the entire face region was blurred due to motion of the subject at the instant of acquisition. If a facial region is not sufficiently well defined then it is marked as a blur defect. In additional or alternatively, another stage of analysis can focus on the eye region of the face(s) to determine if one, or both eyes were fully or partially closed at the instant of acquisition and the face region is categorized accordingly. As mentioned previously, if AAM analysis is performed on the image, then the AAM parameters can be used to indicate whether a subject's eyes are open or not. It should be noted that in the above analyses, the module 90 detects blink or blur due to localized movement of the subject as opposed to global image blur.
[0040] Another or alternative stage of analysis focuses on the mouth region and determines if the mouth is opened in a yawn or indeed not smiling; again the face region is categorized accordingly. As mentioned previously, if AAM analysis is performed on the image, then the AAM parameters can be used to indicate the state of a subject's mouth.
[0041] Other exemplary tests might include luminance levels, skin colour and texture histograms, abrupt facial expressions (smiling, frowning) which may cause significant variations in facial features (mouth shape, furrows in brow). Specialized tests can be implemented as additional or alternative image analysis filters, for example, a Hough transform filter could be used to detect parallel lines in a face region above the eyes indicating a “furrowed brow”. Other image analysis techniques such as those known in the art and as disclosed in U.S. Pat. No. 6,301,440 can also be employed to categorise the face region(s) of the main image.
[0042] After this analysis, it is decided (for each face region) if any of these defects occurred, step 260, and the camera or external processing device user can be offered the option of repairing the defect based on the buffered (low resolution) face region data, step 265.
[0043] When the repair option is actuated by the user, each of the low-resolution face regions is first analyzed by the face region quality analyzer, step 270. As this analysis is operative on lower resolution images acquired and stored at steps 200/210, the analysis may vary from the analysis of face regions in the main acquired image at step 250. Nevertheless the analysis steps are similar in that each low-resolution face region is analyzed to determine if it suffers from image defects in which case it should not be selected at step 280 to reconstruct the defective face region(s) in the main image. After this analysis and selection, if there are not enough “good” face regions corresponding to a defective face region available from the stream of low-resolution images, an indication is passed to the user that image repair is not viable. Where there are enough “good” face regions, these are passed on for resizing and alignment, step 285.
[0044] This step re-sizes each face region and performs some local alignment of cardinal face points to correct for variations in pose and to ensure that each of the low-resolution face regions overlap one another as uniformly as is practical for later processing.
[0045] It should also be noted that as these image regions were captured in sequence and over a relatively short duration, it is expected that they are of approximately the same size and orientation. Thus, image alignment can achieved using cardinal face points, in particular those relating to the eyes, mouth, lower face (chin region) which is normally delineated by a distinct boundary edge, and the upper face which is normally delineated by a distinctive hairline boundary. Some slight scaling and morphing of extracted face regions may be used to achieve reasonable alignment, however a very precise alignment of these images is not desirable as it would undermine the super-resolution techniques which enable a higher resolution image to be determined from several low-resolution images.
[0046] It should be noted that the low-resolution images captured and stored at steps 200/210 can be captured either from a time period before capturing the main image or from a period following capture of the main image (indicated by the dashed line extending from step 230). For example, it may be possible to capture suitable defect free low resolution images in a period immediately after a subject has stopped moving/blinking etc following capture of the main image.
[0047] This set of selected defect free face regions is next passed to a super-resolution module 160 which combines them using known super-resolution methods to yield a high resolution face region which is compatible with a corresponding region of the main acquired image.
[0048] Now the system has available to it, a high quality defect-free combination face region and a high resolution main image with a generally corresponding defective face region.
[0049] If this has not already been performed for quality analysis, the defective face region(s) as well as the corresponding high quality defect-free face region are subjected to AAM analysis, step 300. Referring now to FIG. 3( a) to (d), which illustrates some images including face regions which have been processed by the AAM module 150. In this case, the model represented by the wire frame superimposed on the face is tuned for a generally forward facing and generally upright face, although separate models can be deployed for use with inclined faces or faces in profile. Once the model has been applied, it returns a set of coordinates for the vertices of the wire frame; as well as texture parameters for each of the triangular elements defined by adjacent vertices. The relative coordinates of the vertices as well as the texture parameters can in turn provide indicators linked to the expression and inclination of the face which can be used in quality analysis as mentioned above.
[0050] It will therefore be seen that the AAM module 150 can also be used in the facial region analysis steps 250/270 to provide in indicator of whether a mouth or eyes are open i.e. smiling and not blinking; and also to help determine in steps 285/290 implemented by the super-resolution module 160 whether facial regions are similarly aligned or inclined for selection before super-resolution.
[0051] So, using FIG. 3( a) as an example of a facial region produced by super-resolution of low resolution images, it is observed that the set of vertices comprising the periphery of the AAM model define a region which can be mapped on to corresponding set of peripheral vertices of FIGS. 3( b) to FIG. 3( d) where these images have been classified and confirmed by the user as defective facial regions and candidates for correction.
[0052] In relation to FIG. 4 , the model parameters for FIG. 4( a) or 4(b) which might represent super-resolved defect free face regions could indicate that the left-right orientation of these face regions would not make them suitable candidates for correcting the face region of FIG. 4( c). Similarly, the face region of FIG. 4( f) could be a more suitable candidate than the face region of FIG. 4( e) for correcting the face region of FIG. 4( d).
[0053] In any case, if the super-resolved face region is deemed to be compatible with the defective face region, information from the super-resolved face region can be pasted onto the main image by any suitable technique to correct the face region of the main image, step 320. The corrected image can be viewed and depending on the nature of the mapping, it can be adjusted by the user, before being finally accepted or rejected, step 330. So for example, where dithering around the periphery of the corrected face region is used as part of the correction process, step 320, the degree of dithering can be adjusted. Similarly, luminance levels or texture parameters in the corrected regions can be manually adjusted by the user, or indeed any parameter of the corrected region and the mapping process can be manually adjusted prior to final approval or rejection by the user.
[0054] While AAM provides one approach to determine the outside boundary of a facial region, other well-known image processing techniques such as edge detection, region growing and skin color analysis may be used in addition or as alternatives to AAM. However, these may not have the advantage of also being useful in analysing a face region for defects and/or for pose information. Other techniques which can prove useful include applying foreground/background separation to either the low-resolution images or the main image prior to running face detection to reduce overall processing time by only analysing foreground regions and particularly foreground skin segments. Local colour segmentation applied across the boundary of a foreground/background contour can assist in further refining the boundary of a facial region.
[0055] Once the user is satisfied with the placement of the reconstructed face region they may choose to merge it with the main image; alternatively, if they are not happy they can cancel the reconstruction process. These actions are typically selected through buttons on the camera user interface where the correction module is implemented on the acquisition device 20.
[0056] As practical examples let us consider an example of the system used to correct an eye defect. An example may be used of a defect where one eye is shut in the main image frame due to the subject “blinking” during the acquisition. Immediately after the main image acquisition the user is prompted to determine if they wish to correct this defect. If they confirm this, then the camera begins by analyzing a set of face regions stored from preview images acquired immediately prior to the main image acquisition. It is assumed that a set of, say, 20 images was saved from the one second period immediately prior to image acquisition. As the defect was a blinking eye, the initial testing determines that the last, say, 10 of these preview images are not useful. However the previous 10 images are determined to be suitable. Additional testing of these images might include the determination of facial pose, eliminating images where the facial pose varies more than 5% from the averaged pose across all previews; a determination of the size of the facial region, eliminating images where the averaged size varies more than 25% from the averaged size across all images. The reason the threshold is higher for the latter test is that it is easier to rescale face regions than to correct for pose variations.
[0057] In variations of the above described embodiment, the regions that are combined may include portions of the background region surrounding the main face region. This is particularly important where the defect to be corrected in the main acquired image is due to face motion during image exposure. This will lead to a face region with a poorly defined outer boundary in the main image and the super-resolution image which is superimposed upon it typically incorporates portions of the background for properly correcting this face motion defect. A determination of whether to include background regions for face reconstruction can be made by the user, or may be determined automatically after a defect analysis is performed on the main acquired image. In the latter case, where the defect comprises blurring due to face motion, then background regions will normally be included in the super-resolution reconstruction process. In an alternative embodiment, a reconstructed background can be created using either (i) region infilling techniques for a background region of relatively homogeneous colour and texture characteristics, or (ii) directly from the preview image stream using image alignment and super-resolution techniques. In the latter case the reconstructed background is merged into a gap in the main image background created by the separation of foreground from background; the reconstructed face region is next merged into the separated foreground region, specifically into the facial region of the foreground and finally the foreground is re-integrated with the enhanced background region.
[0058] After applying super-resolution methods to create a higher resolution face region from multiple low-resolution preview images, some additional scaling and alignment operations are normally involved. Furthermore, some blending, infilling and morphological operations may be used in order to ensure a smooth transition between the newly constructed super-resolution face region and the background of the main acquired image. This is particularly the case where the defect to be corrected is motion of the face during image exposure. In the case of motion defects it may also be desirable to reconstruct portions of the image background prior to integration of the reconstructed face region into the main image.
[0059] It is also be desirable to match the overall luminance levels of the new face region with that of the old face region, and this is best achieved through a matching of the skin colour between the old region and the newly constructed one. Preview images are acquired under fixed camera settings and can be over/under exposed. This may not be fully compensated for during the super-resolution process and may involve additional image processing operations.
[0060] While the above described embodiments have been directed to replacing face regions within an image, it will be seen that AAM can be used to model any type of feature of an image. So in certain embodiments, the patches to be used for super-resolution reconstruction may be sub-regions within a face region. For example, it may be desired to reconstruct only a segment of the face regions, such as an eye or mouth region, rather than the entire face region. In such cases, a determination of the precise boundary of the sub-region is of less importance as the sub-region will be merged into a surrounding region of substantially similar colour and texture (i.e. skin colour and texture). Thus, it is sufficient to center the eye regions to be combined or to align the corners of the mouth regions and to rely on blending the surrounding skin coloured areas into the main image.
[0061] In one or more of the above embodiments, separate face regions may be individually tracked (see also U.S. application Ser. No. 11/464,083, which is hereby incorporated by reference). Regions may be tracked from frame-to-frame. Preview or post-view face regions can be extracted, analyzed and aligned with each other and with the face region in the main or final acquired image. In addition, in techniques according to certain embodiments, faces may be tracked between frames in order to find and associate smaller details between previews or post-views on the face. For example, a left eye from Joe's face in preview N may be associated with a left eye from Joe's face in preview N+1. These may be used together to form one or more enhanced quality images of Joe's eye. This is advantageous because small features (an eye, a mouth, a nose, an eye component such as an eye lid or eye brow, or a pupil or iris, or an ear, chin, beard, mustache, forehead, hairstyle, etc. are not as easily traceable between frames as larger features (and their absolute or relative positional shifts between frames tend to be more substantial relative to their size.
[0062] The present invention is not limited to the embodiments described above herein, which may be amended or modified without departing from the scope of the present invention as set forth in the appended claims, and structural and functional equivalents thereof.
[0063] In methods that may be performed according to preferred embodiments herein and that may have been described above and/or claimed below, the operations have been described in selected typographical sequences. However, the sequences have been selected and so ordered for typographical convenience and are not intended to imply any particular order for performing the operations.
[0064] In addition, all references cited above herein, in addition to the background and summary of the invention sections themselves, are hereby incorporated by reference into the detailed description of the preferred embodiments as disclosing alternative embodiments and components. The following are also incorporated by reference for this purpose: U.S. patent applications Nos. 60/829,127, 60/804,546, 60/821,165 11/554,539, 11/464,083, 11/027,001, 10/842,244, 11/024,046, 11/233,513, 11/460,218, 11/573,713, 11/319,766, 11/464,083, 11/744,020 and 11/460,218, and U.S. published application no. 2006/0285754.
Claims
The invention claimed is:
1. An image processing method comprising:
a) acquiring a main image of a scene;
b) determining one or more facial regions in said main image;
c) analysing said one or more facial regions to determine if any one of said facial regions includes a defect;
d) acquiring a sequence of relatively low resolution images nominally of said scene for a time period not including a time for acquiring said main image;
e) determining one or more sets of low resolution facial regions in said sequence of low resolution images;
f) analysing said sets of facial regions to determine if any facial regions of a set corresponding to a defective facial region of said main image include a defect;
g) combining defect free facial regions of said corresponding set to provide a high quality defect free facial region; and
h) correcting at least a portion of any defective facial regions of said main image with image information from a corresponding high quality defect free facial region,
wherein said step f) of analysing further comprises: prior to said combining, removing facial regions including faces exceeding an average size of faces in a set of facial regions by a threshold amount from said set of facial regions.
2. A method according to claim 1 wherein said time period includes one or more of a time period preceding or a time period following said time for acquiring said main image.
3. A method according to claim 1 wherein said correcting step comprises:
applying a model comprising a plurality of vertices defining a periphery of a facial region to each high quality defect free facial region and a corresponding defective facial region; and
mapping pixels of said high quality defect free facial region to said defective facial region according to the correspondence of vertices for said respective regions.
4. A method according to claim 3 wherein said model comprises an Active Appearance Model (AAM).
5. A method according to claim 1 wherein said main image is acquired at an exposure level different to the exposure level of said low resolution images and wherein said correcting comprises mapping luminance levels of said high quality defect free facial region to luminance levels of said defective facial region.
6. A method according to claim 1 comprising storing sets of low resolution facial regions from said sequence of low resolution images in an image header file of said main image.
7. A method according to claim 1 comprising displaying said main image; and responsive to user interaction, performing steps c) and steps f) to h).
8. A method according to claim 1 wherein step e) is performed at a time preceding performing step a).
9. A method according to claim 1 comprising: displaying said corrected image; and responsive to user interaction, saving said corrected image.
10. A method according to claim 1 wherein said step f) of analysing comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial expression; and
prior to said combining, removing faces having a defective expression from said set of facial regions.
11. A method according to claim 1 wherein said step f) of analysing comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial orientation; and
prior to said combining, removing faces having an undesirable orientation from said set of facial regions.
12. A method according to claim 1 wherein said step c) of analysing comprises:
applying an Active Appearance Model (AAM) to each facial region; and
analysing AAM parameters for each facial region to provide an indication of facial expression.
13. A method according to claim 1 wherein said step c) of analysing comprises:
analysing each facial region for one or more of: contrast, sharpness, texture, luminance levels or skin color.
14. A method according to claim 1 wherein said step c) of analysing comprises:
analysing each facial region to determine if any eyes of said facial region are closed.
15. A method according to claim 1 wherein said step c) of analysing comprises:
analysing each facial region to determine if any mouth of said facial region is open.
16. A method according to claim 1 wherein said step c) of analysing comprises:
analysing each facial region to determine if any mouth of said facial region is smiling.
17. A method according to claim 1 wherein steps g) and h) are performed only when said set of facial regions exceeds a given number.
18. A method according to claim 1 comprising: prior to said combining, resizing and aligning faces of said set of facial regions.
19. A method according to claim 18, wherein said aligning is performed according to cardinal points of faces of said set of facial regions.
20. A method according to claim 1 wherein said correcting further comprises one or more of: blending; or infilling a corrected region of said main image with the remainder of said main image.
21. A method according to claim 1 comprising: displaying said corrected image; and responsive to user interaction, adjusting the correction of said corrected image.
22. An image processing method comprising:
a) acquiring a main image of a scene;
b) determining one or more facial regions in said main image;
c) analysing said one or more main image facial regions for defects and determining that one or more are defective;
d) acquiring a sequence of relatively low resolution images nominally of said scene;
e) determining one or more sets of low resolution facial regions in said sequence of low resolution images;
f) analysing said one or more sets of low resolution facial regions to determine one or more that correspond to a defective main image facial region;
g) correcting at least a portion of a defective main image facial region with image information from one or more corresponding low resolution facial regions not including a same defect as said portion of said defective main image facial region,
wherein said step f) of analysing further comprises: prior to said combining, removing facial regions including faces exceeding an average size of faces in a set of facial regions by a threshold amount from said set of facial regions.
23. A method according to claim 22 wherein said correcting comprises:
applying a model comprising a plurality of vertices defining a periphery of a facial region to one or more low resolution facial regions not including said same defect and a corresponding defective main image facial region; and
mapping pixels of said one or more low resolution facial regions to said corresponding defective main image facial region according to the correspondence of vertices for respective regions.
24. A method according to claim 23 wherein said model comprises an Active Appearance Model (AAM).
25. A method according to claim 22 wherein said main image is acquired at an exposure level different than the exposure level of said low resolution images and wherein said correcting comprises mapping luminance levels of one or more low resolution facial regions not have said same defect to luminance levels of said defective main image facial region.
26. A method according to claim 22 comprising storing sets of low resolution facial regions from said sequence of low resolution images in an image header file of said main image.
27. A method according to claim 22, further comprising displaying said main image; and responsive to user interaction, selectively performing said analyzing said one or more facial regions, said analyzing said one of more sets or said correcting, or combinations thereof.
28. A method according to claim 22, further comprising displaying a corrected image based on said correcting, and responsive to user interaction, saving said corrected image.
29. A method according to claim 22, wherein said analysing said one or more sets comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial expression; and
prior to said combining, removing faces having a defective expression from said set of facial regions.
30. A method according to claim 22, wherein said analysing said one or more sets comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial orientation; and
prior to said combining, removing faces having an undesirable orientation from said set of facial regions.
31. A method according to claim 22 wherein said analysing one or more facial regions comprises:
applying an Active Appearance Model (AAM) to each facial region; and
analysing AAM parameters for each facial region to provide an indication of facial expression.
32. A method according to claim 22, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if an eye of said facial region is closed.
33. A method according to claim 22, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if a mouth of said facial region is open.
34. A method according to claim 22, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if a mouth of said facial region is frowning.
35. A method according to claim 22 further comprising displaying a corrected image based on said correcting and responsive to user interaction, adjusting the correcting of said corrected image.
36. A method according to claim 22, wherein said sequence of low resolution images is acquired for a time period not including a time for acquiring said main image.
37. A method according to claim 22, further comprising combining defect-free low resolution facial regions into a combined image, and correcting at least said portion of said defective main image facial region with image information from the combined image.
38. An image processing apparatus comprising:
a) means for acquiring a main image of a scene;
b) means for determining one or more facial regions in said main image;
c) analysing said one or more facial regions to determine if any one of said facial regions includes a defect;
d) means for acquiring a sequence of relatively low resolution images nominally of said scene for a time period not including a time for acquiring said main image;
e) means for determining one or more sets of low resolution facial regions in said sequence of low resolution images;
f) means for analysing said sets of facial regions to determine if any facial regions of a set corresponding to a defective facial region of said main image include a defect;
g) means for combining defect free facial regions of said corresponding set to provide a high quality defect free facial region; and
h) means for correcting at least a portion of any defective facial regions of said main image with image information from a corresponding high quality defect free facial region,
wherein said element f) means for analysing further comprises: means for removing facial regions, prior to said combining, including faces exceeding an average size of faces in a set of facial regions by a threshold amount from said set of facial regions.
39. An image processing apparatus according to claim 38 comprising a digital image acquisition device or general purpose computer or both.
40. An apparatus for providing images with enhanced facial regions in digital images, including a processor and one or more processor-readable media for programming the processor to control the apparatus to perform an image processing method that comprises:
a) acquiring a main image of a scene;
b) determining one or more facial regions in said main image;
c) analysing said one or more main image facial regions for defects and determining that one or more are defective;
d) acquiring a sequence of relatively low resolution images nominally of said scene;
e) determining one or more sets of low resolution facial regions in said sequence of low resolution images;
f) analysing said one or more sets of low resolution facial regions to determine one or more that correspond to a defective main image facial region; and
g) correcting at least a portion of a defective main image facial region with image information from one or more corresponding low resolution facial regions not including a same defect as said portion of said defective main image facial region,
wherein said step f) of analysing further comprises: prior to said combining, removing facial regions including faces exceeding an average size of faces in a set of facial regions by a threshold amount from said set of facial regions.
41. An apparatus according to claim 40, wherein said correcting comprises:
applying a model comprising a plurality of vertices defining a periphery of a facial region to one or more low resolution facial regions not including said same defect and a corresponding defective main image facial region; and
mapping pixels of said one or more low resolution facial regions to said corresponding defective main image facial region according to the correspondence of vertices for respective regions.
42. An apparatus according to claim 41 wherein said model comprises an Active Appearance Model (AAM).
43. An apparatus according to claim 40 wherein said main image is acquired at an exposure level different than the exposure level of said low resolution images and wherein said correcting comprises mapping luminance levels of one or more low resolution facial regions not have said same defect to luminance levels of said defective main image facial region.
44. An apparatus according to claim 40 wherein the method further comprises storing sets of low resolution facial regions from said sequence of low resolution images in an image header file of said main image.
45. An apparatus according to claim 40, wherein the method further comprises displaying said main image; and responsive to user interaction, selectively performing said analyzing said one or more facial regions, said analyzing said one of more sets or said correcting, or combinations thereof.
46. An apparatus according to claim 40, wherein the method further comprises displaying a corrected image based on said correcting, and responsive to user interaction, saving said corrected image.
47. An apparatus according to claim 40, wherein said analysing said one or more sets comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial expression; and
prior to said combining, removing faces having a defective expression from said set of facial regions.
48. An apparatus according to claim 40, wherein said analysing said one or more sets comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial orientation; and
prior to said combining, removing faces having an undesirable orientation from said set of facial regions.
49. An apparatus according to claim 40 wherein said analysing one or more facial regions comprises:
applying an Active Appearance Model (AAM) to each facial region; and
analysing AAM parameters for each facial region to provide an indication of facial expression.
50. An apparatus according to claim 40, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if an eye of said facial region is closed.
51. An apparatus according to claim 40, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if a mouth of said facial region is open.
52. An apparatus according to claim 40, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if a mouth of said facial region is frowning.
53. An apparatus according to claim 40 wherein the method further comprises displaying a corrected image based on said correcting and responsive to user interaction, adjusting the correcting of said corrected image.
54. An apparatus according to claim 40, wherein said sequence of low resolution images is acquired for a time period not including a time for acquiring said main image.
55. An apparatus according to claim 40, wherein the method further comprises combining defect-free low resolution facial regions into a combined image, and correcting at least said portion of said defective main image facial region with image information from the combined image.
56. An image processing method comprising:
a) acquiring a main image of a scene;
b) determining one or more facial regions in said main image;
c) analysing said one or more facial regions to determine if any one of said facial regions includes a defect;
d) acquiring a sequence of relatively low resolution images nominally of said scene for a time period not including a time for acquiring said main image;
e) determining one or more sets of low resolution facial regions in said sequence of low resolution images;
f) analysing said sets of facial regions to determine if any facial regions of a set corresponding to a defective facial region of said main image include a defect;
g) combining defect free facial regions of said corresponding set to provide a high quality defect free facial region; and
h) correcting at least a portion of any defective facial regions of said main image with image information from a corresponding high quality defect free facial region,
wherein said step f) of analysing further comprises: prior to said combining, removing facial regions including faces with an orientation outside an average orientation of faces in a set of facial regions by a threshold amount from said set of facial regions.
57. A method according to claim 56 wherein said time period includes one or more of a time period preceding or a time period following said time for acquiring said main image.
58. A method according to claim 56 wherein said correcting step comprises:
applying a model comprising a plurality of vertices defining a periphery of a facial region to each high quality defect free facial region and a corresponding defective facial region; and
mapping pixels of said high quality defect free facial region to said defective facial region according to the correspondence of vertices for said respective regions.
59. A method according to claim 58 wherein said model comprises an Active Appearance Model (AAM).
60. A method according to claim 56 wherein said main image is acquired at an exposure level different to the exposure level of said low resolution images and wherein said correcting comprises mapping luminance levels of said high quality defect free facial region to luminance levels of said defective facial region.
61. A method according to claim 56 comprising storing sets of low resolution facial regions from said sequence of low resolution images in an image header file of said main image.
62. A method according to claim 56 comprising displaying said main image; and responsive to user interaction, performing steps c) and steps f) to h).
63. A method according to claim 56 wherein step e) is performed at a time preceding performing step a).
64. A method according to claim 56 comprising: displaying said corrected image; and responsive to user interaction, saving said corrected image.
65. A method according to claim 56 wherein said step f) of analysing comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial expression; and
prior to said combining, removing faces having a defective expression from said set of facial regions.
66. A method according to claim 56 wherein said step f) of analysing comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial orientation; and
prior to said combining, removing faces having an undesirable orientation from said set of facial regions.
67. A method according to claim 56 wherein said step c) of analysing comprises:
applying an Active Appearance Model (AAM) to each facial region; and
analysing AAM parameters for each facial region to provide an indication of facial expression.
68. A method according to claim 56 wherein said step c) of analysing comprises:
analysing each facial region for one or more of: contrast, sharpness, texture, luminance levels or skin color.
69. A method according to claim 56 wherein said step c) of analysing comprises:
analysing each facial region to determine if any eyes of said facial region are closed.
70. A method according to claim 56 wherein said step c) of analysing comprises:
analysing each facial region to determine if any mouth of said facial region is open.
71. A method according to claim 56 wherein said step c) of analysing comprises:
analysing each facial region to determine if any mouth of said facial region is smiling.
72. A method according to claim 56 wherein steps g) and h) are performed only when said set of facial regions exceeds a given number.
73. A method according to claim 56 comprising: prior to said combining, resizing and aligning faces of said set of facial regions.
74. A method according to claim 73, wherein said aligning is performed according to cardinal points of faces of said set of facial regions.
75. A method according to claim 56 wherein said correcting further comprises one or more of: blending; or infilling a corrected region of said main image with the remainder of said main image.
76. A method according to claim 56 comprising: displaying said corrected image; and responsive to user interaction, adjusting the correction of said corrected image.
77. An image processing method comprising:
a) acquiring a main image of a scene;
b) determining one or more facial regions in said main image;
c) analysing said one or more main image facial regions for defects and determining that one or more are defective;
d) acquiring a sequence of relatively low resolution images nominally of said scene;
e) determining one or more sets of low resolution facial regions in said sequence of low resolution images;
f) analysing said one or more sets of low resolution facial regions to determine one or more that correspond to a defective main image facial region;
g) correcting at least a portion of a defective main image facial region with image information from one or more corresponding low resolution facial regions not including a same defect as said portion of said defective main image facial region,
wherein said step f) of analysing further comprises: prior to said combining, removing facial regions including faces with an orientation outside an average orientation of faces in a set of facial regions by a threshold amount from said set of facial regions.
78. A method according to claim 77 wherein said correcting comprises:
applying a model comprising a plurality of vertices defining a periphery of a facial region to one or more low resolution facial regions not including said same defect and a corresponding defective main image facial region; and
mapping pixels of said one or more low resolution facial regions to said corresponding defective main image facial region according to the correspondence of vertices for respective regions.
79. A method according to claim 78 wherein said model comprises an Active Appearance Model (AAM).
80. A method according to claim 77 wherein said main image is acquired at an exposure level different than the exposure level of said low resolution images and wherein said correcting comprises mapping luminance levels of one or more low resolution facial regions not have said same defect to luminance levels of said defective main image facial region.
81. A method according to claim 77 comprising storing sets of low resolution facial regions from said sequence of low resolution images in an image header file of said main image.
82. A method according to claim 77, further comprising displaying said main image; and responsive to user interaction, selectively performing said analyzing said one or more facial regions, said analyzing said one of more sets or said correcting, or combinations thereof.
83. A method according to claim 77, further comprising displaying a corrected image based on said correcting, and responsive to user interaction, saving said corrected image.
84. A method according to claim 77, wherein said analysing said one or more sets comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial expression; and
prior to said combining, removing faces having a defective expression from said set of facial regions.
85. A method according to claim 77, wherein said analysing said one or more sets comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial orientation; and
prior to said combining, removing faces having an undesirable orientation from said set of facial regions.
86. A method according to claim 77 wherein said analysing one or more facial regions comprises:
applying an Active Appearance Model (AAM) to each facial region; and
analysing AAM parameters for each facial region to provide an indication of facial expression.
87. A method according to claim 77, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if an eye of said facial region is closed.
88. A method according to claim 77, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if a mouth of said facial region is open.
89. A method according to claim 77, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if a mouth of said facial region is frowning.
90. A method according to claim 77 further comprising displaying a corrected image based on said correcting and responsive to user interaction, adjusting the correcting of said corrected image.
91. A method according to claim 77, wherein said sequence of low resolution images is acquired for a time period not including a time for acquiring said main image.
92. A method according to claim 77, further comprising combining defect-free low resolution facial regions into a combined image, and correcting at least said portion of said defective main image facial region with image information from the combined image.
93. An image processing apparatus comprising:
a) means for acquiring a main image of a scene;
b) means for determining one or more facial regions in said main image;
c) analysing said one or more facial regions to determine if any one of said facial regions includes a defect;
d) means for acquiring a sequence of relatively low resolution images nominally of said scene for a time period not including a time for acquiring said main image;
e) means for determining one or more sets of low resolution facial regions in said sequence of low resolution images;
f) means for analysing said sets of facial regions to determine if any facial regions of a set corresponding to a defective facial region of said main image include a defect;
g) means for combining defect free facial regions of said corresponding set to provide a high quality defect free facial region; and
h) means for correcting at least a portion of any defective facial regions of said main image with image information from a corresponding high quality defect free facial region,
wherein said element f) means for analysing further comprises: means for removing facial regions, prior to said combining, including faces with an orientation outside an average orientation of faces in a set of facial regions by a threshold amount from said set of facial regions.
94. An image processing apparatus according to claim 93 comprising a digital image acquisition device or general purpose computer or both.
95. An apparatus for providing images with enhanced facial regions in digital images, including a processor and one or more processor-readable media for programming the processor to control the apparatus to perform an image processing method that comprises:
a) acquiring a main image of a scene;
b) determining one or more facial regions in said main image;
c) analysing said one or more main image facial regions for defects and determining that one or more are defective;
d) acquiring a sequence of relatively low resolution images nominally of said scene;
e) determining one or more sets of low resolution facial regions in said sequence of low resolution images;
f) analysing said one or more sets of low resolution facial regions to determine one or more that correspond to a defective main image facial region; and
g) correcting at least a portion of a defective main image facial region with image information from one or more corresponding low resolution facial regions not including a same defect as said portion of said defective main image facial region,
wherein said step f) of analysing further comprises: prior to said combining, removing facial regions including faces with an orientation outside an average orientation of faces in a set of facial regions by a threshold amount from said set of facial regions.
96. An apparatus according to claim 95, wherein said correcting comprises:
applying a model comprising a plurality of vertices defining a periphery of a facial region to one or more low resolution facial regions not including said same defect and a corresponding defective main image facial region; and
mapping pixels of said one or more low resolution facial regions to said corresponding defective main image facial region according to the correspondence of vertices for respective regions.
97. An apparatus according to claim 96 wherein said model comprises an Active Appearance Model (AAM).
98. An apparatus according to claim 95 wherein said main image is acquired at an exposure level different than the exposure level of said low resolution images and wherein said correcting comprises mapping luminance levels of one or more low resolution facial regions not have said same defect to luminance levels of said defective main image facial region.
99. An apparatus according to claim 95 wherein the method further comprises storing sets of low resolution facial regions from said sequence of low resolution images in an image header file of said main image.
100. An apparatus according to claim 95, wherein the method further comprises displaying said main image; and responsive to user interaction, selectively performing said analyzing said one or more facial regions, said analyzing said one of more sets or said correcting, or combinations thereof.
101. An apparatus according to claim 95, wherein the method further comprises displaying a corrected image based on said correcting, and responsive to user interaction, saving said corrected image.
102. An apparatus according to claim 95, wherein said analysing said one or more sets comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial expression; and
prior to said combining, removing faces having a defective expression from said set of facial regions.
103. An apparatus according to claim 95, wherein said analysing said one or more sets comprises:
applying an Active Appearance Model (AAM) to each face of a set of facial regions;
analysing AAM parameters for each face of the set of facial regions to provide an indication of facial orientation; and
prior to said combining, removing faces having an undesirable orientation from said set of facial regions.
104. An apparatus according to claim 95 wherein said analysing one or more facial regions comprises:
applying an Active Appearance Model (AAM) to each facial region; and
analysing AAM parameters for each facial region to provide an indication of facial expression.
105. An apparatus according to claim 95, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if an eye of said facial region is closed.
106. An apparatus according to claim 95, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if a mouth of said facial region is open.
107. An apparatus according to claim 95, wherein said analysing one or more facial regions comprises analysing at least one facial region to determine if a mouth of said facial region is frowning.
108. An apparatus according to claim 95 wherein the method further comprises displaying a corrected image based on said correcting and responsive to user interaction, adjusting the correcting of said corrected image.
109. An apparatus according to claim 95, wherein said sequence of low resolution images is acquired for a time period not including a time for acquiring said main image.
110. An apparatus according to claim 95, wherein the method further comprises combining defect-free low resolution facial regions into a combined image, and correcting at least said portion of said defective main image facial region with image information from the combined image.
Patent Citations (356)
| Patent | Date | Inventor | Cited By |
|---|---|---|---|
| US4047187(A) | 1977-09-01 | Mashimo et al. | Applicant |
| US4317991(A) | 1982-03-01 | Stauffer | Applicant |
| US4367027(A) | 1983-01-01 | Stauffer | Applicant |
| USRE31370(E) | 1983-09-01 | Mashimo et al. | Applicant |
| US4448510(A) | 1984-05-01 | Murakoshi | Applicant |
| US4456354(A) | 1984-06-01 | Mizokami | Applicant |
| US4638364(A) | 1987-01-01 | Hiramatsu | Applicant |
| US4690536(A) | 1987-09-01 | Nakai et al. | Applicant |
| US4796043(A) | 1989-01-01 | Izumi et al. | Applicant |
| US4970663(A) | 1990-11-01 | Bedell et al. | Applicant |
| US4970683(A) | 1990-11-01 | Harshaw et al. | Applicant |
| US4975969(A) | 1990-12-01 | Tal | Applicant |
| US5008946(A) | 1991-04-01 | Ando | Applicant |
| US5018017(A) | 1991-05-01 | Sasaki et al. | Applicant |
| USRE33682(E) | 1991-09-01 | Hiramatsu | Applicant |
| US5051770(A) | 1991-09-01 | Cornuejols | Applicant |
| US5063603(A) | 1991-11-01 | Burt | Applicant |
| US5111231(A) | 1992-05-01 | Tokunaga | Applicant |
| US5150432(A) | 1992-09-01 | Ueno et al. | Applicant |
| US5161204(A) | 1992-11-01 | Hutcheson et al. | Applicant |
| US5164831(A) | 1992-11-01 | Kuchta et al. | Applicant |
| US5164992(A) | 1992-11-01 | Turk et al. | Applicant |
| US5227837(A) | 1993-07-01 | Terashita | Applicant |
| US5280530(A) | 1994-01-01 | Trew et al. | Applicant |
| US5291234(A) | 1994-03-01 | Shindo et al. | Applicant |
| US5305048(A) | 1994-04-01 | Suzuki et al. | Applicant |
| US5311240(A) | 1994-05-01 | Wheeler | Applicant |
| US5331544(A) | 1994-07-01 | Lu et al. | Applicant |
| US5353058(A) | 1994-10-01 | Takei | Applicant |
| US5384615(A) | 1995-01-01 | Hsieh et al. | Applicant |
| US5384912(A) | 1995-01-01 | Ogrinc et al. | Applicant |
| US5430809(A) | 1995-07-01 | Tomitaka | Applicant |
| US5432863(A) | 1995-07-01 | Benati et al. | Applicant |
| US5450504(A) | 1995-09-01 | Calia | Applicant |
| US5465308(A) | 1995-11-01 | Hutcheson et al. | Applicant |
| US5488429(A) | 1996-01-01 | Kojima et al. | Applicant |
| US5493409(A) | 1996-02-01 | Maeda et al. | Applicant |
| US5496106(A) | 1996-03-01 | Anderson | Applicant |
| US5576759(A) | 1996-11-01 | Kawamura et al. | Applicant |
| US5633678(A) | 1997-05-01 | Parulski et al. | Applicant |
| US5638136(A) | 1997-06-01 | Kojima et al. | Applicant |
| US5638139(A) | 1997-06-01 | Clatanoff et al. | Applicant |
| US5652669(A) | 1997-07-01 | Liedenbaum | Applicant |
| US5680481(A) | 1997-10-01 | Prasad et al. | Applicant |
| US5684509(A) | 1997-11-01 | Hatanaka et al. | Applicant |
| US5706362(A) | 1998-01-01 | Yabe | Applicant |
| US5710833(A) | 1998-01-01 | Moghaddam et al. | Applicant |
| US5715325(A) | 1998-02-01 | Bang et al. | Applicant |
| US5724456(A) | 1998-03-01 | Boyack et al. | Applicant |
| US5745668(A) | 1998-04-01 | Poggio et al. | Applicant |
| US5764803(A) | 1998-06-01 | Jacquin et al. | Applicant |
| US5771307(A) | 1998-06-01 | Lu et al. | Applicant |
| US5774129(A) | 1998-06-01 | Poggio et al. | Applicant |
| US5774591(A) | 1998-06-01 | Black et al. | Applicant |
| US5774747(A) | 1998-06-01 | Ishihara et al. | Applicant |
| US5774754(A) | 1998-06-01 | Ootsuka | Applicant |
| US5781650(A) | 1998-07-01 | Lobo et al. | Applicant |
| US5802208(A) | 1998-09-01 | Podilchuk et al. | Applicant |
| US5802220(A) | 1998-09-01 | Black et al. | Applicant |
| US5812193(A) | 1998-09-01 | Tomitaka et al. | Applicant |
| US5818975(A) | 1998-10-01 | Goodwin et al. | Applicant |
| US5835616(A) | 1998-11-01 | Lobo et al. | Applicant |
| US5842194(A) | 1998-11-01 | Arbuckle | Applicant |
| US5844573(A) | 1998-12-01 | Poggio et al. | Applicant |
| US5850470(A) | 1998-12-01 | Kung et al. | Applicant |
| US5852669(A) | 1998-12-01 | Eleftheriadis et al. | Applicant |
| US5852823(A) | 1998-12-01 | De Bonet | Applicant |
| USRE36041(E) | 1999-01-01 | Turk et al. | Applicant |
| US5870138(A) | 1999-02-01 | Smith et al. | Applicant |
| US5905807(A) | 1999-05-01 | Kado et al. | Applicant |
| US5911139(A) | 1999-06-01 | Jain et al. | Applicant |
| US5966549(A) | 1999-10-01 | Hara et al. | Applicant |
| US5978519(A) | 1999-11-01 | Bollman et al. | Applicant |
| US5991456(A) | 1999-11-01 | Rahman et al. | Applicant |
| US6028960(A) | 2000-02-01 | Graf et al. | Applicant |
| US6035074(A) | 2000-03-01 | Fujimoto et al. | Applicant |
| US6053268(A) | 2000-04-01 | Yamada | Applicant |
| US6061055(A) | 2000-05-01 | Marks | Applicant |
| US6072094(A) | 2000-06-01 | Karady et al. | Applicant |
| US6097470(A) | 2000-08-01 | Buhr et al. | Applicant |
| US6101271(A) | 2000-08-01 | Yamashita et al. | Applicant |
| US6108437(A) | 2000-08-01 | Lin | Applicant |
| US6128397(A) | 2000-10-01 | Baluja et al. | Applicant |
| US6128398(A) | 2000-10-01 | Kuperstein et al. | Applicant |
| US6134339(A) | 2000-10-01 | Luo | Applicant |
| US6148092(A) | 2000-11-01 | Qian | Applicant |
| US6151073(A) | 2000-11-01 | Steinberg et al. | Applicant |
| US6173068(B1) | 2001-01-01 | Prokoski | Applicant |
| US6188777(B1) | 2001-02-01 | Darrell et al. | Applicant |
| US6192149(B1) | 2001-02-01 | Eschbach et al. | Applicant |
| US6246779(B1) | 2001-06-01 | Fukui et al. | Applicant |
| US6246790(B1) | 2001-06-01 | Huang et al. | Applicant |
| US6249315(B1) | 2001-06-01 | Holm | Applicant |
| US6252976(B1) | 2001-06-01 | Schildkraut et al. | Applicant |
| US6263113(B1) | 2001-07-01 | Abdel-Mottaleb et al. | Applicant |
| US6268939(B1) | 2001-07-01 | Klassen et al. | Applicant |
| US6278491(B1) | 2001-08-01 | Wang et al. | Applicant |
| US6282317(B1) | 2001-08-01 | Luo et al. | Applicant |
| US6301370(B1) | 2001-10-01 | Steffens et al. | Applicant |
| US6301440(B1) | 2001-10-01 | Bolle et al. | Applicant |
| US6332033(B1) | 2001-12-01 | Qian | Applicant |
| US6349373(B2) | 2002-02-01 | Sitka et al. | Applicant |
| US6351556(B1) | 2002-02-01 | Loui et al. | Applicant |
| US6360021(B1) | 2002-03-01 | McCarthy et al. | Examiner |
| US6393148(B1) | 2002-05-01 | Bhaskar | Applicant |
| US6400830(B1) | 2002-06-01 | Christian et al. | Applicant |
| US6404900(B1) | 2002-06-01 | Qian et al. | Applicant |
| US6407777(B1) | 2002-06-01 | DeLuca | Applicant |
| US6421468(B1) | 2002-07-01 | Ratnakar et al. | Applicant |
| US6426779(B1) | 2002-07-01 | Noguchi et al. | Applicant |
| US6438234(B1) | 2002-08-01 | Gisin et al. | Applicant |
| US6438264(B1) | 2002-08-01 | Gallagher et al. | Applicant |
| US6456732(B1) | 2002-09-01 | Kimbell et al. | Applicant |
| US6459436(B1) | 2002-10-01 | Kumada et al. | Applicant |
| US6463163(B1) | 2002-10-01 | Kresch | Applicant |
| US6473199(B1) | 2002-10-01 | Gilman et al. | Applicant |
| US6501857(B1) | 2002-12-01 | Gotsman et al. | Applicant |
| US6502107(B1) | 2002-12-01 | Nishida | Applicant |
| US6504942(B1) | 2003-01-01 | Hong et al. | Applicant |
| US6504951(B1) | 2003-01-01 | Luo et al. | Applicant |
| US6516154(B1) | 2003-02-01 | Parulski et al. | Applicant |
| US6526161(B1) | 2003-02-01 | Yan | Applicant |
| US6529630(B1) | 2003-03-01 | Kinjo | Applicant |
| US6549641(B2) | 2003-04-01 | Ishikawa et al. | Applicant |
| US6556708(B1) | 2003-04-01 | Christian et al. | Applicant |
| US6564225(B1) | 2003-05-01 | Brogliatti et al. | Applicant |
| US6567983(B1) | 2003-05-01 | Shiimori | Applicant |
| US6587119(B1) | 2003-07-01 | Anderson et al. | Applicant |
| US6606398(B2) | 2003-08-01 | Cooper | Applicant |
| US6633655(B1) | 2003-10-01 | Hong et al. | Applicant |
| US6661907(B2) | 2003-12-01 | Ho et al. | Applicant |
| US6697503(B2) | 2004-02-01 | Matsuo et al. | Applicant |
| US6697504(B2) | 2004-02-01 | Tsai | Applicant |
| US6700999(B1) | 2004-03-01 | Yang | Applicant |
| US6747690(B2) | 2004-06-01 | Molgaard | Applicant |
| US6754368(B1) | 2004-06-01 | Cohen | Applicant |
| US6754389(B1) | 2004-06-01 | Dimitrova et al. | Applicant |
| US6760465(B2) | 2004-07-01 | McVeigh et al. | Applicant |
| US6760485(B1) | 2004-07-01 | Gilman et al. | Applicant |
| US6765612(B1) | 2004-07-01 | Anderson et al. | Applicant |
| US6778216(B1) | 2004-08-01 | Lin | Applicant |
| US6792135(B1) | 2004-09-01 | Toyama | Applicant |
| US6801250(B1) | 2004-10-01 | Miyashita | Applicant |
| US6816611(B1) | 2004-11-01 | Hagiwara et al. | Applicant |
| US6829009(B2) | 2004-12-01 | Sugimoto | Applicant |
| US6850274(B1) | 2005-02-01 | Silverbrook et al. | Applicant |
| US6876755(B1) | 2005-04-01 | Taylor et al. | Applicant |
| US6879705(B1) | 2005-04-01 | Tao et al. | Applicant |
| US6885760(B2) | 2005-04-01 | Yamada et al. | Applicant |
| US6900840(B1) | 2005-05-01 | Schinner et al. | Applicant |
| US6937773(B1) | 2005-08-01 | Nozawa et al. | Applicant |
| US6940545(B1) | 2005-09-01 | Ray et al. | Applicant |
| US6959109(B2) | 2005-10-01 | Moustafa | Applicant |
| US6965684(B2) | 2005-11-01 | Chen et al. | Applicant |
| US6977687(B1) | 2005-12-01 | Suh | Applicant |
| US6993157(B1) | 2006-01-01 | Oue et al. | Applicant |
| US7003135(B2) | 2006-02-01 | Hsieh et al. | Applicant |
| US7020337(B2) | 2006-03-01 | Viola et al. | Applicant |
| US7027619(B2) | 2006-04-01 | Pavlidis et al. | Applicant |
| US7027621(B1) | 2006-04-01 | Prokoski | Applicant |
| US7034848(B2) | 2006-04-01 | Sobol | Applicant |
| US7035456(B2) | 2006-04-01 | Lestideau | Applicant |
| US7035462(B2) | 2006-04-01 | White et al. | Applicant |
| US7035467(B2) | 2006-04-01 | Nicponski | Applicant |
| US7038709(B1) | 2006-05-01 | Verghese | Applicant |
| US7038715(B1) | 2006-05-01 | Flinchbaugh | Applicant |
| US7039222(B2) | 2006-05-01 | Simon et al. | Applicant |
| US7042511(B2) | 2006-05-01 | Lin | Applicant |
| US7043465(B2) | 2006-05-01 | Pirim | Applicant |
| US7050607(B2) | 2006-05-01 | Li et al. | Applicant |
| US7057653(B1) | 2006-06-01 | Kubo | Applicant |
| US7064776(B2) | 2006-06-01 | Sumi et al. | Applicant |
| US7082212(B2) | 2006-07-01 | Liu et al. | Applicant |
| US7099510(B2) | 2006-08-01 | Jones et al. | Applicant |
| US7106374(B1) | 2006-09-01 | Bandera et al. | Applicant |
| US7106887(B2) | 2006-09-01 | Kinjo | Applicant |
| US7110569(B2) | 2006-09-01 | Brodsky et al. | Applicant |
| US7110575(B2) | 2006-09-01 | Chen et al. | Applicant |
| US7113641(B1) | 2006-09-01 | Eckes et al. | Applicant |
| US7119838(B2) | 2006-10-01 | Zanzucchi et al. | Applicant |
| US7120279(B2) | 2006-10-01 | Chen et al. | Applicant |
| US7151843(B2) | 2006-12-01 | Rui et al. | Applicant |
| US7158680(B2) | 2007-01-01 | Pace | Applicant |
| US7162076(B2) | 2007-01-01 | Liu | Applicant |
| US7162101(B2) | 2007-01-01 | Itokawa et al. | Applicant |
| US7171023(B2) | 2007-01-01 | Kim et al. | Applicant |
| US7171025(B2) | 2007-01-01 | Rui et al. | Applicant |
| US7190829(B2) | 2007-03-01 | Zhang et al. | Applicant |
| US7194114(B2) | 2007-03-01 | Schneiderman | Applicant |
| US7200249(B2) | 2007-04-01 | Okubo et al. | Applicant |
| US7218759(B1) | 2007-05-01 | Ho et al. | Applicant |
| US7227976(B1) | 2007-06-01 | Jung et al. | Applicant |
| US7254257(B2) | 2007-08-01 | Kim et al. | Applicant |
| US7269292(B2) | 2007-09-01 | Steinberg | Applicant |
| US7274822(B2) | 2007-09-01 | Zhang et al. | Applicant |
| US7274832(B2) | 2007-09-01 | Nicponski | Applicant |
| US7295233(B2) | 2007-11-01 | Steinberg et al. | Applicant |
| US7315630(B2) | 2008-01-01 | Steinberg et al. | Applicant |
| US7315631(B1) | 2008-01-01 | Corcoran et al. | Applicant |
| US7317815(B2) | 2008-01-01 | Steinberg et al. | Applicant |
| US7336821(B2) | 2008-02-01 | Ciuc et al. | Applicant |
| US7362368(B2) | 2008-04-01 | Steinberg et al. | Applicant |
| US7403643(B2) | 2008-07-01 | Ianculescu et al. | Applicant |
| US7408581(B2) | 2008-08-01 | Gohda | Examiner |
| US7440593(B1) | 2008-10-01 | Steinberg et al. | Applicant |
| US7515740(B2) | 2009-04-01 | Corcoran et al. | Applicant |
| US7612794(B2) | 2009-11-01 | He et al. | Applicant |
| US7620214(B2) | 2009-11-01 | Chen et al. | Applicant |
| US7636485(B2) | 2009-12-01 | Simon et al. | Applicant |
| US7764311(B2) | 2010-07-01 | Bill | Examiner |
| US2001/0005222(A1) | 2001-06-01 | Yamaguchi | Applicant |
| US2001/0028731(A1) | 2001-10-01 | Covell et al. | Applicant |
| US2001/0031142(A1) | 2001-10-01 | Whiteside | Applicant |
| US2001/0038712(A1) | 2001-11-01 | Loce et al. | Applicant |
| US2001/0038714(A1) | 2001-11-01 | Masumoto et al. | Applicant |
| US2002/0090116(A1) | 2002-07-01 | Miichi et al. | Examiner |
| US2002/0105662(A1) | 2002-08-01 | Patton et al. | Applicant |
| US2002/0106114(A1) | 2002-08-01 | Yan et al. | Applicant |
| US2002/0114535(A1) | 2002-08-01 | Luo | Applicant |
| US2002/0118287(A1) | 2002-08-01 | Grosvenor et al. | Applicant |
| US2002/0136433(A1) | 2002-09-01 | Lin | Applicant |
| US2002/0150662(A1) | 2002-10-01 | Dewis et al. | Applicant |
| US2002/0168108(A1) | 2002-11-01 | Loui et al. | Applicant |
| US2002/0172419(A1) | 2002-11-01 | Lin et al. | Applicant |
| US2002/0176609(A1) | 2002-11-01 | Hsieh et al. | Applicant |
| US2002/0181801(A1) | 2002-12-01 | Needham et al. | Applicant |
| US2002/0191861(A1) | 2002-12-01 | Cheatle | Applicant |
| US2003/0012414(A1) | 2003-01-01 | Luo | Applicant |
| US2003/0023974(A1) | 2003-01-01 | Dagtas et al. | Applicant |
| US2003/0025812(A1) | 2003-02-01 | Slatter | Applicant |
| US2003/0035573(A1) | 2003-02-01 | Duta et al. | Applicant |
| US2003/0048950(A1) | 2003-03-01 | Savakis et al. | Applicant |
| US2003/0052991(A1) | 2003-03-01 | Stavely et al. | Applicant |
| US2003/0059107(A1) | 2003-03-01 | Sun et al. | Applicant |
| US2003/0059121(A1) | 2003-03-01 | Savakis et al. | Applicant |
| US2003/0071908(A1) | 2003-04-01 | Sannoh et al. | Applicant |
| US2003/0084065(A1) | 2003-05-01 | Lin et al. | Applicant |
| US2003/0107649(A1) | 2003-06-01 | Flickner et al. | Applicant |
| US2003/0118216(A1) | 2003-06-01 | Goldberg | Applicant |
| US2003/0123713(A1) | 2003-07-01 | Geng | Applicant |
| US2003/0123751(A1) | 2003-07-01 | Krishnamurthy et al. | Applicant |
| US2003/0142209(A1) | 2003-07-01 | Yamazaki et al. | Applicant |
| US2003/0151674(A1) | 2003-08-01 | Lin | Applicant |
| US2003/0169907(A1) | 2003-09-01 | Edwards et al. | Applicant |
| US2003/0202715(A1) | 2003-10-01 | Kinjo | Applicant |
| US2004/0022435(A1) | 2004-02-01 | Ishida | Applicant |
| US2004/0095359(A1) | 2004-05-01 | Simon et al. | Applicant |
| US2004/0120391(A1) | 2004-06-01 | Lin et al. | Applicant |
| US2004/0120399(A1) | 2004-06-01 | Kato | Applicant |
| US2004/0170397(A1) | 2004-09-01 | Ono | Applicant |
| US2004/0175021(A1) | 2004-09-01 | Porter et al. | Applicant |
| US2004/0179719(A1) | 2004-09-01 | Chen et al. | Applicant |
| US2004/0218832(A1) | 2004-11-01 | Luo et al. | Applicant |
| US2004/0223649(A1) | 2004-11-01 | Zacks et al. | Applicant |
| US2004/0228505(A1) | 2004-11-01 | Sugimoto | Applicant |
| US2004/0264744(A1) | 2004-12-01 | Zhang et al. | Applicant |
| US2005/0013479(A1) | 2005-01-01 | Xiao et al. | Applicant |
| US2005/0041121(A1) | 2005-02-01 | Steinberg et al. | Applicant |
| US2005/0068446(A1) | 2005-03-01 | Steinberg et al. | Applicant |
| US2005/0068452(A1) | 2005-03-01 | Steinberg et al. | Applicant |
| US2005/0069208(A1) | 2005-03-01 | Morisada | Applicant |
| US2005/0089218(A1) | 2005-04-01 | Chiba | Applicant |
| US2005/0104848(A1) | 2005-05-01 | Yamaguchi et al. | Applicant |
| US2005/0105780(A1) | 2005-05-01 | Ioffe | Applicant |
| US2005/0140801(A1) | 2005-06-01 | Prilutsky et al. | Applicant |
| US2005/0169536(A1) | 2005-08-01 | Accomazzi et al. | Examiner |
| US2005/0185054(A1) | 2005-08-01 | Edwards et al. | Applicant |
| US2005/0275721(A1) | 2005-12-01 | Ishii | Applicant |
| US2006/0006077(A1) | 2006-01-01 | Mosher et al. | Applicant |
| US2006/0008152(A1) | 2006-01-01 | Kumar et al. | Applicant |
| US2006/0008173(A1) | 2006-01-01 | Matsugu et al. | Applicant |
| US2006/0018517(A1) | 2006-01-01 | Chen et al. | Applicant |
| US2006/0029265(A1) | 2006-02-01 | Kim et al. | Applicant |
| US2006/0039690(A1) | 2006-02-01 | Steinberg et al. | Applicant |
| US2006/0050933(A1) | 2006-03-01 | Adam et al. | Applicant |
| US2006/0098875(A1) | 2006-05-01 | Sugimoto | Applicant |
| US2006/0098890(A1) | 2006-05-01 | Steinberg et al. | Applicant |
| US2006/0120599(A1) | 2006-06-01 | Steinberg et al. | Applicant |
| US2006/0140455(A1) | 2006-06-01 | Costache et al. | Applicant |
| US2006/0147192(A1) | 2006-07-01 | Zhang et al. | Applicant |
| US2006/0177100(A1) | 2006-08-01 | Zhu et al. | Applicant |
| US2006/0177131(A1) | 2006-08-01 | Porikli | Applicant |
| US2006/0203106(A1) | 2006-09-01 | Lawrence et al. | Applicant |
| US2006/0203107(A1) | 2006-09-01 | Steinberg et al. | Applicant |
| US2006/0203108(A1) | 2006-09-01 | Steinberg et al. | Applicant |
| US2006/0204034(A1) | 2006-09-01 | Steinberg et al. | Applicant |
| US2006/0204054(A1) | 2006-09-01 | Steinberg et al. | Applicant |
| US2006/0204055(A1) | 2006-09-01 | Steinberg et al. | Applicant |
| US2006/0204056(A1) | 2006-09-01 | Steinberg et al. | Applicant |
| US2006/0204057(A1) | 2006-09-01 | Steinberg | Applicant |
| US2006/0204058(A1) | 2006-09-01 | Kim et al. | Applicant |
| US2006/0204110(A1) | 2006-09-01 | Steinberg et al. | Applicant |
| US2006/0210264(A1) | 2006-09-01 | Saga | Applicant |
| US2006/0215924(A1) | 2006-09-01 | Steinberg et al. | Applicant |
| US2006/0257047(A1) | 2006-11-01 | Kameyama et al. | Applicant |
| US2006/0268150(A1) | 2006-11-01 | Kameyama et al. | Applicant |
| US2006/0269270(A1) | 2006-11-01 | Yoda et al. | Applicant |
| US2006/0280380(A1) | 2006-12-01 | Li | Applicant |
| US2006/0285754(A1) | 2006-12-01 | Steinberg et al. | Applicant |
| US2006/0291739(A1) | 2006-12-01 | Li et al. | Applicant |
| US2007/0018966(A1) | 2007-01-01 | Blythe et al. | Applicant |
| US2007/0070440(A1) | 2007-03-01 | Li et al. | Applicant |
| US2007/0071347(A1) | 2007-03-01 | Li et al. | Applicant |
| US2007/0091203(A1) | 2007-04-01 | Peker et al. | Applicant |
| US2007/0098303(A1) | 2007-05-01 | Gallagher et al. | Applicant |
| US2007/0110305(A1) | 2007-05-01 | Corcoran et al. | Applicant |
| US2007/0116379(A1) | 2007-05-01 | Corcoran et al. | Applicant |
| US2007/0116380(A1) | 2007-05-01 | Ciuc et al. | Applicant |
| US2007/0122056(A1) | 2007-05-01 | Steinberg et al. | Applicant |
| US2007/0133901(A1) | 2007-06-01 | Aiso | Applicant |
| US2007/0154095(A1) | 2007-07-01 | Cao et al. | Applicant |
| US2007/0154096(A1) | 2007-07-01 | Cao et al. | Applicant |
| US2007/0160307(A1) | 2007-07-01 | Steinberg et al. | Applicant |
| US2007/0189606(A1) | 2007-08-01 | Ciuc et al. | Applicant |
| US2007/0189748(A1) | 2007-08-01 | Drimbarean et al. | Applicant |
| US2007/0189757(A1) | 2007-08-01 | Steinberg et al. | Applicant |
| US2007/0201724(A1) | 2007-08-01 | Steinberg et al. | Applicant |
| US2007/0201725(A1) | 2007-08-01 | Steinberg et al. | Examiner |
| US2007/0201750(A1) | 2007-08-01 | Ito et al. | Examiner |
| US2007/0237421(A1) | 2007-10-01 | Luo et al. | Examiner |
| US2007/0296833(A1) | 2007-12-01 | Corcoran et al. | Applicant |
| US2008/0013798(A1) | 2008-01-01 | Ionita et al. | Applicant |
| US2008/0037827(A1) | 2008-02-01 | Corcoran et al. | Applicant |
| US2008/0037838(A1) | 2008-02-01 | Ianculescu et al. | Applicant |
| US2008/0037839(A1) | 2008-02-01 | Corcoran et al. | Applicant |
| US2008/0037840(A1) | 2008-02-01 | Steinberg et al. | Applicant |
| US2008/0043122(A1) | 2008-02-01 | Steinberg et al. | Applicant |
| US2008/0049970(A1) | 2008-02-01 | Ciuc et al. | Applicant |
| US2008/0055433(A1) | 2008-03-01 | Steinberg et al. | Applicant |
| US2008/0075385(A1) | 2008-03-01 | David et al. | Applicant |
| US2008/0144966(A1) | 2008-06-01 | Steinberg et al. | Applicant |
| US2008/0175481(A1) | 2008-07-01 | Petrescu et al. | Applicant |
| US2008/0205712(A1) | 2008-08-01 | Ionita et al. | Applicant |
| US2008/0240555(A1) | 2008-10-01 | Nanu et al. | Applicant |
| US2009/0052750(A1) | 2009-02-01 | Steinberg et al. | Applicant |
| EP1128316(A1) | 2001-08-01 | Applicant | |
| EP1626569(A1) | 2006-02-01 | Applicant | |
| EP1887511(A1) | 2008-02-01 | Applicant | |
| GB2370438(A1) | 2002-06-01 | Applicant | |
| JP5260360(A2) | 1993-10-01 | Applicant | |
| JP25164475(A2) | 2005-06-01 | Applicant | |
| JP26005662(A2) | 2006-01-01 | Applicant | |
| JP26254358(A2) | 2006-09-01 | Applicant | |
| WO2052835(A2) | 2002-07-01 | Applicant | |
| WO2007095477(A2) | 2007-08-01 | Applicant | |
| WO2007095477(A3) | 2007-08-01 | Applicant | |
| WO2007095483(A2) | 2007-08-01 | Applicant | |
| WO2007095553(A2) | 2007-08-01 | Applicant | |
| WO2007095553(A3) | 2007-08-01 | Applicant | |
| WO2007142621(A1) | 2007-12-01 | Applicant | |
| WO2008015586(A2) | 2008-02-01 | Applicant | |
| WO2008015586(A3) | 2008-02-01 | Applicant | |
| WO2008018887(A1) | 2008-02-01 | Applicant | |
| WO2008023280(A2) | 2008-02-01 | Applicant | |
| WO2008104549(A2) | 2008-09-01 | Applicant | |
| WO2008/150285(A1) | 2008-12-01 | Applicant |
Non-Patent Literature (93)
- Bradski Gary et al., “Learning-Based Computer Vision with Intel's Open Source Computer Vision Library”, Intel Technology. 2005, pp. 119-130, vol. 9—Issue 2.Applicant
- Corcoran, P. et al., “Automatic Indexing of Consumer Image Collections Using Person Recognition Techniques”, Digest of Technical Papers. International Conference on Consumer Electronics, 2005, pp. 127-128.Applicant
- Costache, G. et al., “In-Camera Person-Indexing of Digital Images”, Digest of Technical Papers. International Conference on Consumer Electronics, 2006, pp. 339-340.Applicant
- Demirkir, C. et al., “Face detection using boosted tree classifier stages”, Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, 2004, pp. 575-578.Applicant
- Drimbarean, A.F. et al., “Image Processing Techniques to Detect and Filter Objectionable Images based on Skin Tone and Shape Recognition”, International Conference on Consumer Electronics, 2001, pp. 278-279.Applicant
- Viola, P. et al., “Rapid Object Detection using a Boosted Cascade of Simple Features”, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, pp. 1-511-1-518, vol. 1.Applicant
- Viola, P. et al., “Robust Real-Time Face Detection”, International Journal of Computer Vision, 2004, pp. 137-154, vol. 57—Issue 2, Kluwer Academic Publishers.Applicant
- Xin He et al., “Real-Time Human Face Detection in Color Image”, International Conference on Machine Learning and Cybernetics, 2003, pp. 2915-2920, vol. 5.Applicant
- Zhao, W. et al., “Face recognition: A literature survey, ISSN: 0360-0300, http://portal.acm.org/citation.cfm?id=954342andcoll=GUIDEanddl=GUIDEandCFID=680-9268andCFTOKEN=82843223.”, ACM Computing Surveys (CSUR) archive, 2003, pp. 399-458, vol. 35—Issue 4, ACM Press.Applicant
- Zhu Qiang et al., “Fast Human Detection Using a Cascade of Histograms of Oriented Gradients”. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, pp. 1491-1498, IEEE Computer Society.Applicant
- Aoki, Hiroyuki et al., “An Image Storage System Using Complex-Valued Associative Memories, Abstract printed from http://csdl.computer.org/comp/proceedings/icpr/2000/0750/ 02/07502626abs.htm”, International Conference on Pattern Recognition (ICPR '00), 2000, vol. 2.Applicant
- Batur et al., “Adaptive Active Appearance Models”, IEEE Transactions on Image Processing, 2005, pp. 1707-1721, vol. 14—Issue 11.Applicant
- Beraldin, J.A. et al., “Object Model Creation from Multiple Range Images: Acquisition, Calibration, Model Building and Verification, Abstract printed from http://csdl.computer.org/comp/proceedings/nrc/1997/7943/00/79430326abs.htm”, International Conference on Recent Advances in 3-D Digital Imaging and Modeling, 1997.Applicant
- Beymer, David, “Pose-Invariant face Recognition Using Real and Virtual Views, A.I. Technical Report No. 1574”, Massachusetts Institute of Technology Artificial Intelligence Laboratory, 1996, pp. 1-176.Applicant
- Buenaposada, J., “Efficiently estimating 1-3,16 facial expression and illumination in appearance-based tracking, Retrieved from the Internet: URL:http://www.bmva.ac.uk/bmvc/2006/ [retrieved on Sep. 1, 2008]”, Proc. British machine vision conference, 2006.Applicant
- Chang, T. et al., “Texture Analysis and Classification with Tree-Structured Wavelet Transform”, IEEE Trans. on Image Proc., 1993, pp. 429-441, vol. 2—Issue 4.Applicant
- Cootes T. et al., “Modeling Facial Shape and Appearance, S. Li and K. K. Jain (Eds.): ”Handbook of face recognition“, XP002494037”, 2005, Chapter 3, Springer.Applicant
- Cootes, T.F. and Taylor, C.J., “On representing edge structure for model matching”, Proc. IEEE Computer Vision and Pattern Recognition, 2001, pp. 1114-1119.Applicant
- Cootes, T.F. et al., “A comparative evaluation of active appearance model algorithms”, Proc. 9th British Machine Vison Conference. British Machine Vision Association, 1998, pp. 680-689.Applicant
- Crowley, J., “Multi-modal tracking of faces for video communication, http://citeseer.ist.psu.edu/crowley97multimodal.html”, In Computer Vision and Patent Recognition, 1997.Applicant
- Dalton, John, “Digital Cameras and Electronic Color Image Acquisition, Abstract printed from http://csdl.computer.org/comp/proceedings/compcon/1996/7414/00/7414043labs.htm”, COMPCON Spring '96—41st IEEE International Conference, 1996.Applicant
- Analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, pp. 1690-1694, vol. 28—Issue 10.Applicant
- Edwards, G.J. et al., “Advances in active appearance models”, International Conference on Computer Vision (ICCV'99), 1999, pp. 137-142.Applicant
- Edwards; G.J. et al., “Learning to identify and track faces in image sequences, Automatic Face and Gesture Recognition”, IEEE Comput. Soc, 1998, pp. 260-265.Applicant
- Feraud, R. et al.. “A Fast and Accurate Face Detector Based on Neural Networks”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, pp. 42-53, vol. 23—Issue 1.Applicant
- Froba, B., “Face detection with the modified census transform”, Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004, pp. 91-96.Applicant
- Froba, B. et al., “Real time face detection, Kauai, Hawai Retrieved from the Internet:URL:http://www.embassi.de/publi/veroeffent/Froeba.pdf [retrieved on Oct. 23, 2007]”, Dept. of Applied Electronics, Proceedings of lasted “Signal and Image Processing”, 2002, pp. 1-6.Applicant
- Garnaoui, H.H. et al., “Visual Masking and the Design of Magnetic Resonance Image Acquisition, Abstract printed from http://csdl.computer.org/comp/proceedings/icip/1995/7310/ 01/73100625abs.htm”. International Conference on Image Processing, 1995, vol. 1.Applicant
- Gaubatz, Mathew et al., “Automatic Red-Eye Detection and Correction”, IEEE ICIP, Proceedings 2002 International Conf. on Image Proc., 2002, pp. 1-804-1-807, vol. 2—Iss. 3.Applicant
- Gerbrands. J., “On the Relationships Between SVD. KLT, and PCA”, Pattern Recognition, 1981, pp. 375-381, vol. 14, Nos. 1-6.Applicant
- Goodall. C., “Procrustes Methods in the Statistical Analysis of Shape, Stable URL: hup://www.jstor.org/stable/2345744”, Journal of the Royal Statistical Society. Series B (Methodological), 1991, pp. 285-339, vol. 53—Issue 2, Blackwell Publishing for the Royal Statistical Society.Applicant
- Hou, XinWen et al., “Direct Appearance Models”, IEEE, 2001, pp. I-828-I-833.Applicant
- Hu, Wen-chen et al., “A Line String Image Representation for Image Storage and Retrieval, Abstract printed from http://csdl.computer.oro/comp/proceedings/icmcs/1997/7819/00/78190434 abs.htm”. Intl. Conf. on Multimedia Computing and Systems, 1997.Applicant
- Huang, J. et al., “Detection of human faces using decision trees, http://doLieeecomputersociety.org/10.1109/Recognition”, 2nd International Conference on Automatic Face and Gesture Recognition (FG '96), IEEE Xplore, 2001, p. 248.Applicant
- Huang et al., “Image Indexing Using Color Correlograms”, Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97), 1997, pp. 762.Applicant
- Huber, Reinhold et al., “Adaptive Aperture Control for Image Acquisition, Abstract printed from http://csdl.computer.org/comp/proceedings/wacv/2002/1858/00/18580320abs.htm. cited by other”, Sixth IEEE Workshop on Applications of Computer Vision, 2002.Applicant
- Jebara, Tony, “3D Pose Estimation and Normalization for Face Recognition, A Thesis submitted to the Faculty of Graduate Studies and Research in Partial fulfillment of the requirements of the degree of Bachelor of Engineering”, Dept. of Elect. Eng., 1996, pp. 1-121, McGill Univ.Applicant
- Jones, M., “Fast multi-view face detection, http://www.merl.com/papers/docs/TR2003-96.pdf”, Mitsubishi Elect. Research Lab, 2003, 10 pgs.Applicant
- Kang, Sing Bing et al., “A Multibaseline Stereo System with Active Illumination and Real-Time Image Acquisition, Abstract printed from http://csdl.computer.org/comp/proceedings/iccv/1995/7042/00/70420088abs.htm”, Fifth International Conference on Computer Vision, 1995.Applicant
- Kita, Nobuyuki et al., “Archiving Technology for Plant Inspection Images Captured by Mobile Active Cameras—4D Visible Memory, Abstract printed from http://csdl.computer.org/comp/proceedings/3dpvt/2002/1521/00/15210208abs.htm”, 1st International Symposium on 3D Data Processing Visualization and Transmission (3DPVT '02), 2002.Applicant
- Kouzani, A.Z., “Illumination-Effects Compensation in Facial Images Systems”, Man and Cybernetics, IEEE SMC '99 Conference Proceedings, 1999, pp. VI-840-VI-844, vol. 6.Applicant
- Kozubek, Michal et al., “Automated Multi-view 3D Image Acquisition in Human Genome Research, Abstract printed from http://csdl.computer.org/comp/proceedings/3pvt/2002/1521/00/15210091abs.htm”, 1st Intl Symp. on 3D Data Proc. Visualization and Trans. (3DPVT '02), 2002.Applicant
- Krishnan, Arun, Panoramic Image Acquisition, 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96), Jun. 18-20, 1996, San Francisco, CA, Abstract printed from http://csdl.computer.org/comp/proceedings/cvpr/1996/7258/00/72580379abs.htm.Applicant
- Lai, J.H. et al., “Face recognition using holistic Fourier in variant features, http://digitalimaging.inf.brad.ac.uk/publication/pr34-1.pdf.”, Patt. Recog., 2001, pp. 95-109, vol. 34.Applicant
- Lei et al., “A CBIR Method Based on Color-Spatial Feature”, IEEE 10th Ann. Int. Conf., 1999.Applicant
- Lienhart, R. et al., “A Detector Tree of Boosted Classifiers for Real-Time Object Detection and Tracking”, Proceedings of the 2003 International Conference on Multimedia and Expo, 2003, pp. 277-280, vol. 1, IEEE Computer Society.Applicant
- Matkovic, Kresimir et al., “The 3D Wunderkammer an Indexing by Placing Approach to the Image Storage and Retrieval, Abst. printed http://csdl.computer.org/comp/proccedings/tocg/2003/1942/00/19420034abs.htm”, Theory and Practice of Comp. Graphics, 2003, Univ. of Birmingham.Applicant
- Matthews, I. et al., “Active appearance models revisited, Retrieved from http://www.d.cmu.edu/pub—files/pub4/matthews—iain—2004—2/matthews—iain—2004—2.pdf”. International Journal of Computer Vision, 2004, pp. 135-164, vol. 60—Issue 2.Applicant
- Mekuz, N. et al., “Adaptive Step Size Window Matching for Detection”, Proceedings of the 18th International Conference on Patient Recognition, 2006, pp. 259-262, vol. 2.Applicant
- Mitra, S. et al., “Gaussian Mixture Models Based on the Frequency Spectra for Human Identification and Illumination Classification”, Proceedings of the Fourth IEEE Workshop on Automatic Identification Advanced Technologies, 2005, pp. 245-250.Applicant
- Nordstrøm, M.M. et al., “The IMM face database an annotated dataset of 240 face images, http://www2.imin.dtu.dk/pubdb/p.php?3160”, Informatics and Mathematical Modelling, 2004.Applicant
- Ohta, Y-I et al., “Color Information for Region Segmentation, XP008026458”, Computer Graphics and Image Processing, 1980, pp. 222-241, vol. 13—Issue 3, Academic Press.Applicant
- Park, Daechul et al., “Lenticular Stereoscopic Imaging and Displaying Techniques with no Special Glasses, Abstract printed from http://csdl.computer.org/comp/proceedings/icip/1995/7310/03/73103137abs.htm”, International Conference on Image Processing, 1995, vol. 3.Applicant
- PCT Invitation to Pay Additional Fees and, Where Applicable Protest Fee, for PCT Application No. PCT/EP2008/001578, paper dated Jul. 8, 2008, 5 Pages.Applicant
- PCT Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority, or the Declaration, for PCT Application No. PCT/US2006/021393, dated Mar. 29, 2007, 12 pages.Applicant
- PCT Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority, or the Declaration, for PCT Application No. PCT/EP2007/006540, Nov. 8, 2007. 11 pgs.Applicant
- PCT Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority, or the Declaration, for PCT Application No. PCT/EP2008/052329, dated Sep. 15, 2008, 12 pages.Applicant
- PCT Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority, or the Declaration, for PCT Application No. PCT/IB2007/003724, dated Aug. 28, 2008, 9 pages.Applicant
- PCT Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority, or the Declaration, for PCT Application No. PCT/EP2007/006540, Nov. 7, 2008, 6 pgs.Applicant
- PCT Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority, or the Declaration, for PCT Application No. PCT/US2006/021393, dated Mar. 29, 2007, 12 pages.Applicant
- PCT Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority, or the Declaration, for PCT Application No. PCT/US2006/60392, 9 pages, dated Sep. 19, 2008.Applicant
- Romdhani, S. et al., “Face Identification by Fitting a 3D Morphable Model using linear Shape and Texture Error Functions, XP003018283”, European Conf. on Comp. Vision, 2002, pp. 1-15.Applicant
- Rowley, Henry et al., “Neutral Network-Based Face Detection”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, pp. 23-28, vol. 20—Issue 1.Applicant
- Ryu et al., “Coarse-to-Fine Classification for Image-Based Face Detection”, 1999, p. 92, subsection 8.3, Chapter 6, Carnegie Melon Univ.Applicant
- Ryu, Hanjin et al., “Coarse-to-Fine Classification for Image-Based Face Detection”, Image and video retrieval lecture notes in Computer science, 2006, pp. 291-299, vol. 4071, Springer-Verlag.Applicant
- Shand, M., “Flexible Image Acquisition Using Reconfigurable Hardware, Abstract printed from http://csdl.computer.org/comp/proceedings/fccm/1995/7086/00/70860125abs.htm”, IEEE Symposium of FPGA's for Custom Computing Machines (FCCM '95), 1995.Applicant
- Sharma, G., “Digital color imaging, [Online]. Available: citeseer.ist.psu.edu/shanna97digital.html”, IEEE Transactions on Image Processing, 1997, pp. 901932, vol. 6—Issue 7.Applicant
- Sim, T. et al., “The CMU Pose. Illumination, and Expression (PIE) database, Automatic Face and Gesture Recognition”, Proceeding, Fifth IEEE International Conference on, IEEE Piscataway, NJ, USA., pp. 53-58, 2002.Applicant
- Skocaj, Danijel, “Range Image Acquisition of Objects with Non-Uniform Albedo Using Structured Light Range, Sensor, Abstract printed from http://csdl.computer.org/comp/proceedings/icpr/2000/0750/01/07501778abs.htm”, Intl Conf. on Pattern Rec. (ICPR '00), 2000, vol. 1.Applicant
- Smeraldi, F. et al., “Facial feature detection by saccadic exploration of the Gabor decomposition, XP010586874”, Image Processing, ICIP 98. Proc. International Conf. Chicago, IL, USA, IEEE Comput. Soc, 1998, pp. 163-167, vol. 3.Applicant
- Soriano, M. et al., “Making Saturated Facial Images Useful Again, XP002325961, ISSN: 0277-786X”, Proceedings of The Spie, 1999, pp. 113-121, vol. 3826.Applicant
- Stegmann, M. B. et al., “A flexible appearance modelling environment, Available: http://www2.imm.dtu.dk/pubdb/p.php?1918”, IEEE Transactions on Medical Imaging, 2003, pp. 1319-1331, vol. 22—Issue 10.Applicant
- Stegmann, M.B. et al., “Multi-band modelling of appearance, XP009104697”, Image and Vision Computing, 2003, pp. 61-67, vol. 21—Issue 1.Applicant
- Stricker et al., “Similarity of color images”, SPIE Proc, 1995, pp. 1-12, vol. 2420.Applicant
- Sublett, J.W. et al., “Design and Implementation of a Digital Teleultrasound System for Real-Time Remote Diagnosis, Abstract printed from http://csdl.computer.org/comp/proccedings/cbms/1995/7117/00/71170292abs.htm”, Eight Annual IEEE Symposium on Computer-Based Medical Systems (CBMS '95), 1995.Applicant
- Tang, Yuan Y. et al., “Information Acquisition and Storage of Forms in Document Processing, Abstract printed from http://csdl.computer.org/comp/proceedings/icdar/1997/7898/00/78980170abs.htm”, 4th Intl Conference Document Analysis and Recognition, 1997, vol. I and II.Applicant
- Tjahyadi et al., “Application of the DCT Energy Histogram for Face Recognition”, Proceedings of the 2nd Intl. Conf. on Information Technology for Application, 2004, pp. 305-310.Applicant
- Tkalcic, M., “Colour spaces perceptual, historical and applicational background, ISBN: 0-7803-7763-X”, IEEE, EUROCON, 2003, pp. 304-308, vol. 1.Applicant
- Turk, Matthew et al., “Eigenfaces for Recognition”, Journal of Cognitive Neuroscience, 1991, 17 pgs, vol. 3—Issue 1.Applicant
- Twins Crack Face Recognition Puzzle, Internet Article: printed Mar. 10, 2003, 3 pages, http://www.cnn.com/2003/TECH/ptech/03/10/israel.twins.reut/index.html.Applicant
- U.S. Appl. No. 11/554,539, filed Oct. 30, 2006, entitled Digital Image Processing Using Face Detection And Skin Tone Information.Applicant
- Vuylsteke, P. et al., “Range Image Acquisition with a Single Binary-Encoded Light Pattern, abstract printed from http://csdl.computer.org/comp/trans/tp/1990/02/i0148abs.htm”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 1 page.Applicant
- Wan, S.J. et al., “Variance-based color image quantization for frame buffer display”, S. K. M. Wong Color Research and Application, 1990, pp. 52-58, vol. 15—Issue 1.Applicant
- Yang, M-H. et al., “Detecting Faces in Images: A Survey, ISSN:0162-8828, http://portal.acm.org/citation.cfm?id=505621andcoll=GUIDEanddl=GUIDEandCFID=680-9268andCFTOKEN=82843223.”, IEEE Transactions on Pattern Analysis and Machine Intelligence archive, 2002, pp. 34-58, vol. 24—Issue 1, IEEE Computer Society.Applicant
- Zhang, Jun et al., “Face Recognition: Eigenface, Elastic Matching, and Neural Nets”, Proceedings of the IEEE, 1997, pp. 1423-1435, vol. 85—Issue 9.Applicant
- Final Office Action mailed Nov. 18, 2009, for U.S. Appl. No. 11/554,539, filed Oct. 30, 2006.Applicant
- Non-Final Office Action mailed Aug 19, 2009, for U.S. Appl. No. 11/773,815, filed Jul. 5, 2007.Applicant
- Non-Final Office Action mailed Aug 20, 2009, for U.S. Appl. No. 11/773,855, filed Jul. 5, 2007.Applicant
- Non-Final Office Action mailed Jan. 20, 2010, for U.S. Appl. No. 12/262,024, filed Oct. 30, 2008.Applicant
- Non-Final Office Action mailed Sep. 8, 2009, for U.S. Appl. No. 11/688,236, filed Mar. 19, 2007.Applicant
- Notice of Allowance mailed Sep. 28, 2009, for U.S. Appl. No. 12/262,037, filed Oct. 30, 2008.Applicant
- PCT Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority, or the Declaration, for PCT Application No. PCT/US2007/069593, dated Sep. 16, 2008, 9 pages.Applicant
- PCT International Preliminary Report on Patentability, for PCT Application No. PCT/US2007/069593, dated Nov. 24, 2009, 4 pages.Applicant