CTNF 18/870,095 CTNF 99206 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia 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 07-20-aia AIA 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. 07-21-aia AIA Claim (s) 1-2, 4, 6-10, 12, 15, 18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Sun (Made of reference in ids: X. Sun, L. Huang and C. Liu, "Multimodal Face Spoofing Detection via RGB-D Images," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 2018, pp. 2221-2226, doi: 10.1109/ICPR.2018.8545849.) in view of Cheng (US 20200175260 A1) . Regarding claim 1, Sun teaches An image processing apparatus comprising: a region division unit configured to generate a partial region by dividing an entire region of an image (Fig.1 and right column of page 2223: teaches dividing a normalized face image into multiple subregions.); and a comparison unit configured to compare estimated 3D information with sensor 3D information with use of the partial region( Fig.1, section a, b and d:Teaches use image subregions to perform analysis between rgb image information and depth information), but fails to teach wherein the estimated 3D information is 3D information estimated on a basis of the image, and the sensor 3D information is 3D information acquired by a sensor and associated with the image. Cheng Teaches wherein the estimated 3D information is 3D information estimated on a basis of the image (Para. 59 and 63: teaches generating Angular Spherical face representation from image/ depth image data to describe facial geometry. It would have been obvious to incorporate image-based 3d representation techniques of Cheng into the RGB-D anti-spoofing framework of Sun in order to improve analysis of facial geometry and provide a more robust comparison). Regarding claim 2, Sun in view of Cheng teaches The image processing apparatus according to claim 1, wherein the region division unit detects an object that is main and is to be a subject in the image, and divides the entire region on a basis of a detection result (Sun, Fig.1 and section a: detects the face through facial landmark localization and face normalization. The detected face region is then selected for subsequent processing.). Regarding claim 4, Sun in view of Cheng teaches The image processing apparatus according to claim 1, wherein the comparison unit compares the sensor 3D information and the estimated 3D information for each of the partial regions ( Sun, Fig.1, p 2224, left hand column, first paragraph: teaches comparing image information and sensor acquired depth information through multimodal correlation analysis). Regarding claim 6, Sun in view of Cheng teaches The image processing apparatus according to claim 1, wherein the comparison unit compares a difference between the 3D information of the partial region and the 3D information of a region surrounding the partial region, between the estimated 3D information and the sensor 3D information (Sun, Pg.2223 right column: The cross entropy computation measures differences/consistency between the depth distribution of regions.pg.2223 right column also teach each segmented face patch represents a partial region. Cheng, Para 66: teaches angular and distance-based bins inherently define regions surrounding other localized regions around an anchor point) . Regarding claim 7, Sun in view of Cheng teaches The image processing apparatus according to claim 1, wherein the comparison unit compares the estimated 3D information and the sensor 3D information by using a plurality of techniques ( Sun, abstract, p.2222 -2224: teaches multiple comparison approaches including cca-based multimodal correlation and cross entropy based depth consistency analysis). Regarding claim 8, Sun in view of Cheng teaches The image processing apparatus according to claim 1, further comprising: a presentation processing unit configured to generate presentation information indicating a determination result of authenticity of the partial region of the image or a determination result of authenticity of the entire image (Sun, abstract, p.2222- p 2223. Right column and fig.1: the final classifier generates information indicative of the authenticity determination, on a basis of a comparison result obtained with use of the partial region between the estimated 3D information and the sensor 3D information (Sun, pg.2222- pg.2223: The final authenticity determination is based on comparison results derived from the analyzed facial regions ). Regarding claim 9, Sun in view of Cheng teaches The image processing apparatus according to claim 8, wherein the presentation information includes at least either of visual information or auditory information (Sun, Fig.1 : the output of genuine or spoof in inherently a visual presentation to a user since the classifier result is displayed or otherwise presented as information indicating authenticity). Regarding claim 10, Sun in view of Cheng teaches The image processing apparatus according to claim 8, wherein in a case where the authenticity is suspicious on a basis of the comparison result, the presentation processing unit generates the presentation information including a warning indicating suspicion of the authenticity (Sun, Fig.1 : the output of genuine or spoof in inherently a visual presentation to a user since the classifier result is displayed or otherwise presented as information indicating authenticity). Regarding claim 12, Sun in view of Cheng teaches The image processing apparatus according to claim 8, wherein in a case where the image is a moving image, the region division unit divides the entire region for every frame and generates the partial region (Sun, Section 3 and section c page 2224: teaches frame level spoof and genuine classification and video level classification via voting.), the comparison unit compares the estimated 3D information and the sensor 3D information with use of the partial region for the every frame (Sun, Section B depth consistency analysis: teaches computing depth consistency between regions and compares histograms/ cross-entropies among facial subregions. This section also teaches using both color and depth information from corresponding regions), and the presentation processing unit generates the presentation information on a basis of the comparison result for every frame (Cheng Para.42, 94 and 99-100 and Sun fig : teaches output/authenticity indication). Regarding claim 15, Sun in view of Cheng teaches The image processing apparatus according to claim 8, further comprising:a presentation unit configured to present the presentation information (Cheng. Para 94: output manager 1040 and fig.11). Regarding claim 18, Sun in view of Cheng teaches The image processing apparatus according to claim 1, further comprising:a sensor 3D information acquisition unit configured to acquire the sensor 3D information corresponding to the image (Sun, Abstract and p 2221-2224 and page 2224: the Kinect depth sensor acquires the depth information corresponding to the captured RGB image), wherein the comparison unit compares the estimated 3D information with the sensor 3D information acquired by the sensor 3D information acquisition unit ( Sun, Abstract and page 2222-2223: the system analyzes correlations between image-derived information and Kinect-acquired depth information). Regarding claim 20, Sun teaches An image processing method comprising: generating a partial region by dividing an entire region of an image; (Fig.1 and right column of page 2223: teaches dividing a normalized face image into multiple subregions.); and a comparison unit configured to compare estimated 3D information with sensor 3D information with use of the partial region( Fig.1, section a, b and d:Teaches use image subregions to perform analysis between rgb image information and depth information), but fails to teach wherein the estimated 3D information is 3D information estimated on a basis of the image, and the sensor 3D information is 3D information acquired by a sensor and associated with the image. Cheng Teaches wherein the estimated 3D information is 3D information estimated on a basis of the image (Para. 59 and 63: teaches generating Angular Spherical face representation from image/ depth image data to describe facial geometry. It would have been obvious to incorporate image-based 3d representation techniques of Cheng into the RGB-D anti-spoofing framework of Sun in order to improve analysis of facial geometry and provide a more robust comparison) . 07-21-aia AIA Claim (s) 3 is rejected under 35 U.S.C. 103 as being unpatentable over Sun (Made of reference in ids: X. Sun, L. Huang and C. Liu, "Multimodal Face Spoofing Detection via RGB-D Images," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 2018, pp. 2221-2226, doi: 10.1109/ICPR.2018.8545849.) in view of Cheng (US 20200175260 A1) in further view of Yamamoto (US-20220319038-A1) . Regarding claim 3, Sun in view of Cheng teaches The image processing apparatus according to claim 1, wherein the region division unit divides the entire region (Sun: fig.1 teaches dividing image region) but fails to teach by clustering the estimated 3D information. YAMAMOTO Teaches clustering the estimated 3d information (Para.320: teaches dividing points corresponding to three dimensional coordinates into two or more regions and assigning the points to the regions using Euclidean cluster. It would have been obvious to combine the clustering technique of Yamamoto into the system of Sun in view of Cheng in order to improve the accuracy of the region based 3D analysis) . 07-21-aia AIA Claim (s) 11 is rejected under 35 U.S.C. 103 as being unpatentable over Sun (Made of reference in ids: X. Sun, L. Huang and C. Liu, "Multimodal Face Spoofing Detection via RGB-D Images," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 2018, pp. 2221-2226, doi: 10.1109/ICPR.2018.8545849.) in view of Cheng (US 20200175260 A1) in further view of Tian (US-20210358149-A1) . Regarding claim 11, Sun in view of Cheng teaches The image processing apparatus according to claim 8, wherein in a case where the authenticity is suspicious on a basis of the comparison result, but fails to teach the presentation processing unit generates the presentation information clearly indicating a region for which the authenticity is suspicious. Tian Teaches the presentation processing unit generates the presentation information clearly indicating a region for which the authenticity is suspicious ( Para.29: highlighting of legible contours of suspicious areas of a face image. It would have been obvious to incorporate the suspicious area highlighting technique of Tian into the spoof detection system of Sun in view of Cheng in order to provide users with visual feedback identifying regions responsible for the spoof determination) . 07-21-aia AIA Claim (s) 13 is rejected under 35 U.S.C. 103 as being unpatentable over Sun (Made of reference in ids: X. Sun, L. Huang and C. Liu, "Multimodal Face Spoofing Detection via RGB-D Images," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 2018, pp. 2221-2226, doi: 10.1109/ICPR.2018.8545849.) in view of Cheng (US 20200175260 A1) in further view of Kawasaki (US-12418624-B2) . Regarding claim 13, Sun in view of Cheng teaches The image processing apparatus according to claim 12, but fails to teach wherein the presentation processing unit generates the presentation information indicating in which a region for which the authenticity is suspicious is present in the moving image. Kawasaki teaches a range in a time direction which the authenticity is suspicious is present in the moving image (Claim 1: teaches presenting/storing information over a temporal range of a video surrounding a detected event. A POSITA would have found it obvious to incorporate the teachings of Kawasaki into the system of Sun in view of Cheng by using temporal range of a video to detect an event.) . 07-21-aia AIA Claim (s) 14 is rejected under 35 U.S.C. 103 as being unpatentable over Sun (Made of reference in ids: X. Sun, L. Huang and C. Liu, "Multimodal Face Spoofing Detection via RGB-D Images," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 2018, pp. 2221-2226, doi: 10.1109/ICPR.2018.8545849.) in view of Cheng (US 20200175260 A1) in further view of Lee (US-20150149180-A1) . Regarding claim 14, Sun in view of Cheng teaches The image processing apparatus according to claim 12, wherein the presentation processing unit generates an image of a frame in which a region for which the authenticity is suspicious is present (Sun fig.1). Sun in view of Cheng Fails to teach generating a reduced image of a frame. LEE teaches generating a reduced image of a frame (Para. 21: teaches generating a reduced size image/ thumbnails and displaying that reduced size image to a user in conjunction with event information. A POSITA would have found it obvious to incorporate the teachings of Lee’s generation of a reduced image/thumbnail into the system of Sun in view of Cheng in order to make spoof detection results easier for the user to review) . 07-21-aia AIA Claim (s) 16 is rejected under 35 U.S.C. 103 as being unpatentable over Sun (Made of reference in ids: X. Sun, L. Huang and C. Liu, "Multimodal Face Spoofing Detection via RGB-D Images," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 2018, pp. 2221-2226, doi: 10.1109/ICPR.2018.8545849.) in view of Cheng (US 20200175260 A1) in further view of Kawasaki (US-12418624-B2) . Regarding claim 16, Sun in view of Cheng teaches The image processing apparatus according to claim 8, indicates a confirmation result in the presentation information (Sun, Fig.1 : results showing genuine or spoof). Sun in view of Cheng Fails to teach wherein the presentation processing unit confirms validity of an electronic signature corresponding to the image. Che teaches wherein the presentation processing unit confirms validity of an electronic signature corresponding to the image ( Para. 44, 47-48 and 50: teaches a digital signature corresponding to the image/ authentication data is generated and verified. It would have been obvious to combine the teachings of Che digital signature authentication with an image with the system of Sun in view of Cheng in order to give more accurate authentication for facial images)) . 07-21-aia AIA Claim (s) 17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Sun (Made of reference in ids: X. Sun, L. Huang and C. Liu, "Multimodal Face Spoofing Detection via RGB-D Images," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 2018, pp. 2221-2226, doi: 10.1109/ICPR.2018.8545849.) in view of Cheng (US 20200175260 A1) in further view of Hu (Made of reference in ids: US-20210009080-A1) . Regarding claim 17, Sun in view of Cheng teaches The image processing apparatus according to claim 1, further comprising: but fails to teach an estimation unit configured to estimate the 3D information corresponding to the image on a basis of the image, and generate the estimated 3D information, wherein the comparison unit compares the estimated 3D information generated by the estimation unit with the sensor 3D information. Hu teaches an estimation unit configured to estimate the 3D information corresponding to the image on a basis of the image ( Para 148: teaches a depth map updated based on the first image to obtain a second depth map, and generate the estimated 3D information ( Para 134, 146 and 148: teaches generating the second depth map), wherein the comparison unit compares the estimated 3D information generated by the estimation unit with the sensor 3D information (Para. 182,185, 187-188 and 277-278: teaches the image based depth estimation/update of the target region and the interaction between the estimated depth map and the original sensor depth map. It would have been obvious to combine the teachings of Hu with the system of Sun in view of Cheng to improve spoof detection accuracy by using image based depth estimation to supplement and refine sensor acquired depth information. ). Regarding claim 19, Sun in view of Cheng teaches The image processing apparatus according to claim 1, further comprising: an image file acquisition unit configured to acquire an original image and an image file storing the sensor 3D information corresponding to the original image ( Sun, Page. 2224 : the region division unit generates the partial region), wherein the region division unit generates the partial region corresponding to a processed image obtained by processing the original image by dividing the entire region of the original image stored in the image file (Sun, page.2223: and fig.1 teaches dividing the entire region and generating partial region), and the comparison unit compares the sensor 3D information with the estimated 3D information of the partial region, the estimated 3D information being estimated on a basis of the original image (Hu, Para. 182,185, 187-188 and 277-278: teaches the image based depth estimation/update of the target region and the interaction between the estimated depth map and the original sensor depth map.) . Allowable Subject Matter Claim 5 is objected to as allowable subject matter. The following is a statement of reasons for the indication of allowable subject matter: None of the prior art teaches such limitations “herein the comparison unit derives a first relative positional relationship between the partial regions by comparing the sensor 3D information between the partial regions, derives a second relative positional relationship between the partial regions by comparing the estimated 3D information between the partial regions, and compares the first relative positional relationship with the second relative positional relationship.” Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Fujimoto (US 20250182287 A1): discloses combining 2d image data with sensor derived 3d information to process images and extract object regions. Tate et al (US 20160148070 A1): discloses dividing an entire image into regions and generating partial regions. Any inquiry concerning this communication or earlier communications from the examiner should be directed to LATRELL ANTHONY CREARY whose telephone number is (703)756-1219. The examiner can normally be reached Mon - Fri 7:30am - 4:30pm. 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, Xiao WU can be reached on (571) 272-7761. 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. /LATRELL ANTHONY CREARY/Examiner, Art Unit 2613 /XIAO M WU/Supervisory Patent Examiner, Art Unit 2613 Application/Control Number: 18/870,095 Page 2 Art Unit: 2613 Application/Control Number: 18/870,095 Page 3 Art Unit: 2613 Application/Control Number: 18/870,095 Page 4 Art Unit: 2613 Application/Control Number: 18/870,095 Page 5 Art Unit: 2613 Application/Control Number: 18/870,095 Page 6 Art Unit: 2613 Application/Control Number: 18/870,095 Page 7 Art Unit: 2613 Application/Control Number: 18/870,095 Page 8 Art Unit: 2613 Application/Control Number: 18/870,095 Page 9 Art Unit: 2613 Application/Control Number: 18/870,095 Page 11 Art Unit: 2613 Application/Control Number: 18/870,095 Page 12 Art Unit: 2613 Application/Control Number: 18/870,095 Page 13 Art Unit: 2613
Prosecution Insights