Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-7 are rejected under 35 U.S.C. 103 as being unpatentable over Clippingdale (Japan Patent Pub. No.: JP2011039869A), hereinafter Clippingdale, in view of Hu (Chinese Patent Pub. No.: CN104021380B), hereinafter Hu, further in view of Hillebrand (US Patent Pub. No.: US 2009/0028380 A1), hereinafter Hillebrand.
Regarding claim 1, Clippingdale teaches a matching support apparatus comprising: at least one memory configured to store instructions (Further, the "computer-readable recording medium" refers to a portable recording medium such as a flexible disk, a magneto-optical disk, an optical disk, or a memory card, or a storage device such as a hard disk built in the computer system. [0171]); and at least one processor (The present invention relates to an image processing technique, and more particularly, to an image processing apparatus and a computer program for processing a face image. [0001]) configured to execute the instructions to: generate a first feature information including position information (The face region detection/ collation unit 120 reads video data from the image data storage unit 110, detects a face image region for each image frame, and estimates the positions of a plurality of feature points. [0020]) on a reference face development image (Returning to FIG. 1, the three dimensional estimation unit 130 estimates a three dimensional position of each feature point, and warps a mesh shape of a generic (person unspecified) three dimensional computer graphics face mesh model (three dimensional CG face model, generic model) to the estimated position. [0023]) of a feature region designated by a user (In step S604, the face area detection/ collation unit 120 detects a face image area from the read image frame. [0035]. When a face image is registered, the position (coordinates) of each feature point in the registered face image is designated by an operation of a pointing device or the like by a registrant, and a plurality of Gabor Wavelet (Gabor wavelet) features are measured from a neighboring region centered on each feature point. [0004]) on the reference face development image generated based on three-dimensional data of a head serving as a reference (Returning to FIG. 1, the three dimensional estimation unit 130 estimates a three dimensional position of each feature point, and warps a mesh shape of a generic (person unspecified) three dimensional computer graphics face mesh model (three dimensional CG face model, generic model) to the estimated position. [0023]) displayed on the screen of a display device (The output unit 8 causes the estimated value of the three dimensional model of the face of the subject to be displayed on a display or printed by a printer or the like. [0104]); convert a second feature information including position information (The face region detection/ collation unit 120 reads video data from the image data storage unit 110, detects a face image region for each image frame, and estimates the positions of a plurality of feature points. [0020]) on the reference face development image (Returning to FIG. 1, the three dimensional estimation unit 130 estimates a three dimensional position of each feature point, and warps a mesh shape of a generic (person unspecified) three dimensional computer graphics face mesh model (three dimensional CG face model, generic model) to the estimated position. [0023]) of a feature region designated by a user (In step S604, the face area detection/ collation unit 120 detects a face image area from the read image frame. [0035]. When a face image is registered, the position (coordinates) of each feature point in the registered face image is designated by an operation of a pointing device or the like by a registrant, and a plurality of Gabor Wavelet (Gabor wavelet) features are measured from a neighboring region centered on each feature point. [0004]) on the reference face development image generated based on three-dimensional data of a head serving as a reference (Returning to FIG. 1, the three dimensional estimation unit 130 estimates a three dimensional position of each feature point, and warps a mesh shape of a generic (person unspecified) three dimensional computer graphics face mesh model (three dimensional CG face model, generic model) to the estimated position. [0023]), displayed on the screen of the display device (The output unit 8 causes the estimated value of the three dimensional model of the face of the subject to be displayed on a display or printed by a printer or the like. [0104]); acquire a matching information including position information on a matching-use face development image of a matching-use feature region (The feature point information uses a feature point number (an integer starting from 0) as a key, and holds a visibility flag indicating whether a feature point corresponding to the feature point number is visible or invisible, a feature point two dimensional coordinate value of the feature point (however, the two dimensional coordinate value is indicated only in a case where the visibility flag is visible), and a value of a Gabor wavelet feature (image information) in a predetermined number of resolutions (wavelet sizes) a predetermined number of orientations in association with each other. [0031]), in which the matching-use face development image for each person registered in advance and the matching-use feature region on the matching-use face development image are associated with each other (FIG. 5 is a schematic diagram illustrating a data structure of a variable template structure generated by the database registration unit 150. The variable template structure shown in the figure has, for each registered person, person identification information including the name of the registered person or a name for specifying the registered person, and identification information. Each person has head posture indices (angle data) corresponding to the number of head postures. Furthermore, each head posture index has feature point information corresponding to the number of feature points. [0031]); match the feature information with the position information by using the position information included in the feature information and the position information included in the matching information (The face image region detection/ collation unit 120 performs a search by measuring Gabor wavelet features from a low resolution region to a high resolution region. The Gabor wavelet features are complex numbers in which the cosine waveform of the real part and the sine waveform of the imaginary part are 90 degrees out of phase. Therefore, the face region detection / collation unit 120 estimates the positional deviation using the coefficients of the real part and the imaginary part, and repeatedly performs the search process while shifting the position. Then, the search processing is ended at the time when the positional deviation is converged. The position at this time is estimated to be the feature point position at which the similarity is the maximum, that is, the estimated feature point two dimensional coordinate value. [0036]); select a matching Information to serve as a candidate from the matching information for each person registered in advance based on a matching result (When the recognition mode is set, the face region detection / collation unit 120 calculates the similarity with the face feature data of each registered person stored in the face feature database unit 160, and outputs the match score of the face feature data having the highest similarity. The match score is, for example, information in which the name of the registered person or a name (nickname or the like) for specifying the registered person, identification information (identification number or the like) of the same person, and the calculated similarity are associated with each other. [0021]).
Clippingdale does not expressly teach the following limitations as further recited, but Hu further teaches convert a second feature information including position information (Fig. 2 222b) on the reference face development image (In one embodiment, the process of performing facial recognition may include dividing the target image 202 and the reference image 201 into multiple regions. [0028]) of a feature region designated by a user on the reference face development image (Therefore, the regions corresponding to local features 222a and 222b in the reference image can be compared with the corresponding regions in the target image. [0028]), in which the first information (Fig. 2 222a) is displayed on the screen of the display device (
PNG
media_image1.png
312
460
media_image1.png
Greyscale
).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Clippingdale to incorporate the teachings of Hu to convert a second feature information including position information on the reference face development image of a feature region designated by a user on the reference face development image, in which the first information is displayed on the screen of the display device, in order to determine if there is a face recognition match between the target image and the reference image.
The combination of Clippingdale and Hu does not teach the following limitations as further recited, but Hillebrand further teaches output a display information for displaying the matching-use face development image included in the selected matching information on the screen of the display device (It can be observed that the wrinkle-aged simulated image (FIG. 11D) based on the images of age 28 agrees well with the age 37 image (FIG. 11C) (which reads on “the matching-use face development image included in the selected matching information”) in terms of the appearance of wrinkles. [0102].
PNG
media_image2.png
488
616
media_image2.png
Greyscale
).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Hillebrand to output a display information for displaying the matching-use face development image included in the selected matching information on the screen of the display device for ease of comparison.
Regarding claim 2, Clippingdale in the combination teaches the matching support apparatus according to claim 1, wherein the one or more processors further: calculates a matching index as the matching result (When the recognition mode is set, the face region detection / collation unit 120 calculates the similarity with the face feature data of each registered person stored in the face feature database unit 160, and outputs the match score of the face feature data having the highest similarity. [0021]), using a value indicating an approximateness of a position of the feature region to a position of the matching-use feature region, or a deviation between the position of the feature region and the position of the matching-use feature region (Further, an estimated value of the positional deviation between the measurement position on the recognition target face image and the position at which the similarity is maximized is calculated. [0005]), or a relationship between the position of the feature region and the position of the matching-use feature region, or a combination thereof.
Regarding claim 3, Hillebrand in the combination teaches the matching support apparatus according to claim 1, wherein the one or more processors further: detects the feature region from an image, displayed on the screen of the display device, including the face of the person targeted for matching (In FIGS. 12B, 12D, 12F and 12H, the wrinkles that are detected within the region delimited by the polygon 1200 are shown highlighted. [0103]. To demonstrate the accuracy of the aging-simulation method of the present invention, the actual age 37 image of the subject in the same region-of-interest (which reads on “the face of the person targeted for matching”) is shown in FIG. 12G column along with the corresponding wrinkles-detected image in FIG. 12H. [0105].
PNG
media_image3.png
462
608
media_image3.png
Greyscale
), and associates the position of the detected feature region with a corresponding position on the reference face development image (It can be observed that the wrinkle-aged simulated image (FIG. 11D) (which reads on “the reference face development image”) based on the images of age 28 agrees well with the age 37 image (FIG. 11C) in terms of the appearance of wrinkles (which reads on “the position of the detected feature region”). [0102].
PNG
media_image4.png
488
616
media_image4.png
Greyscale
).
Regarding claim 4, Clippingdale in the combination teaches the matching support apparatus according to claim 1, wherein the matching-use face development image is development image of the face cylindrically projected (
PNG
media_image5.png
704
932
media_image5.png
Greyscale
) by executing UV development processing using the three-dimensional data of the head of each of a plurality of persons registered in advance (If a texture is attached (mapped) to a corrected three dimensional CG face model generated by warping a face image of video data in accordance with the three dimensional CG face model, when the corrected three dimensional CG face model after mapping is rendered in an arbitrary head posture, the face texture of the person to be registered is reflected in the head posture. Since the quality of the texture reflected on the surface of the rendered modified three dimensional CG face model is determined by the UV texture image in addition to the head posture, the illumination condition, and the like, the UV texture image is modified as follows in order to match the model with the face of a specific person. [0058]).
Regarding claim 5, Hillebrand in the combination teaches the matching support apparatus according to claim 1, wherein the facial feature and the matching-use feature region are at least any one or more of moles, freckles, tattoos, birthmarks, wrinkles, dimples, scars, warts, lumps, rough skin and discolored skin patches, which are visible on the skin surface of the person (It can be observed that the wrinkle-aged simulated image (FIG. 11D) based on the images of age 28 agrees well with the age 37 image (FIG. 1C) in terms of the appearance of wrinkles. [0102]).
Method claim 6 is drawn to the method of using the corresponding apparatus claimed in claim 1. Therefore method claim 6 corresponds to apparatus claim 1 and is rejected for the same reasons of obviousness as used above.
Claim 7 is drawn to a non-transitory computer-readable recording medium having executable instructions stored for executing the method of using the corresponding apparatus as claimed in claim 1. Therefore, claim 7 corresponds to apparatus claim 1, and is rejected for the same reasons of obviousness as used above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEI ZHAO whose telephone number is (703)756-1922. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, VU LE can be reached at (571)272-7332. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/LEI ZHAO/Examiner, Art Unit 2668
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights