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 Objections
The numbering of claims is not in accordance with 37 CFR 1.126 which requires the original numbering of the claims to be preserved throughout the prosecution. When claims are canceled, the remaining claims must not be renumbered. When new claims are presented, they must be numbered consecutively beginning with the number next following the highest numbered claims previously presented (whether entered or not).
Misnumbered claim 21 been renumbered 20.
Misnumbered claim 22 been renumbered 21.
Status of Claims
Claims 1, 3 – 12 and 14 – 21 remain pending.
Claims 1, 3 – 6, 12 and 14 – 19 are Amended
Claims 2 and 13 have been canceled.
Claims 20 and 21 are new claims.
Response to Arguments
Applicant's arguments filed April 23, 2026 with respect to claims 1, 3 – 12 and 14 – 21
have been considered but are moot because the new grounds of rejection do not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Response to Remarks
Applicant argues that Sakamoto is silent on the following limitations below. Examiner respectfully disagrees for the reasons provided below:
In the Remarks (p. 8) regarding claim 1, applicants assert, “Sakamoto's second teacher data generator 115 "converts the framed equivalent image included in the first teacher data having the annotation information added thereto into an image having predetermined distortion (hereinafter, referred to as a distorted image) to generate the second teacher data." Sakamoto, paragraph [0034]. This conversion reintroduces optical distortion characteristics that simulate lens-induced distortion for training purposes. Sakamoto does not teach intentionally introducing distortions by digital processing to specific segments while maintaining other segments unchanged, as recited by amended claims 1, 12, and 19”.
Examiner respectfully disagrees because Sakamoto in [0060] and Fig. 5 discloses, “The second teacher data generator 115 converts the framed equivalent images imgC(L), imgC(C), imgC(R) into distorted images imgD(L), imgD(C) and imgD(R) having predetermined distortion to generate second teacher data. The learning model generator 116 generates a first learning model on the basis of the distorted image imgD(L), generates a second learning model on the basis of the distorted image imgD(C) and generates a third learning model on the basis of the distorted image imgD(R)”. Sakamoto in [0060] discloses imgC(L), imgC(C), and imgC(R) are separate image segments and those regions are converted into distorted image while maintaining other segments of the image unchanged.
For the reasons above, the rejections of claims 1, 3 – 12 and 14 – 21 as established in the last Office Action (Non-Final, 07/09/2025) are proper and are hereby maintained and incorporated in this Office Action.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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, 5, 10 – 12, 17 – 19 are rejected under 35 U.S.C 103 as being unpatentable over Sakamoto et al. US Patent Application Publication No. US-20190197669-A1 (hereinafter Sakamoto) in view of Fu Patent Application Publication No. CN-113469898-A (hereinafter Fu) and Phillipp Patent Application Publication No. US-20220217272-A1 (hereinafter Phillipp).
Regarding claim 1, Sakamoto discloses a method for defect detection, the method comprises: receiving an image of an evaluated object (Sakamoto in [0027] discloses, “the data acquirer 111 stores image data of a captured image received (or input) from an external device in the storage 150 as the captured image 151”); applying a distortion removal machine learning process on the image to provide a processed image of the evaluated object; wherein the distortion removal machine learning process is trained by a training process to remove distortions from images of objects (Sakamoto in [0028 - 0029] discloses, “The image corrector 112 generates an image (hereinafter referred to as an equivalent image because distortion has been corrected ... The object detector 113 detects a target object from an equivalent image generated by the image corrector 112 ”. And [0035] discloses about the machine learning model); and wherein the training process comprises feeding the machine learning process with images of reference objects and with distorted images of the reference objects; wherein the distorted images are generated by distorting the images of the reference (Sakamoto discloses in Fig. 3 S111 wherein frame equivalent image is the images of the reference object and second teacher data is the distorted images of the reference objects); wherein a distorting of an image of a defect free object comprises replacing segments of the image by distorted segments while maintaining other segments of the image unchanged; wherein a distorted segment is generated by intentionally introducing, by digital processing, a difference in one or more properties of a corresponding segment of the image (Sakamoto in [0060] and Fig. 5 discloses, “The second teacher data generator 115 converts the framed equivalent images imgC(L), imgC(C), imgC(R) into distorted images imgD(L), imgD(C) and imgD(R) having predetermined distortion to generate second teacher data. The learning model generator 116 generates a first learning model on the basis of the distorted image imgD(L), generates a second learning model on the basis of the distorted image imgD(C) and generates a third learning model on the basis of the distorted image imgD(R)”. Sakamoto in [0060] discloses imgC(L), imgC(C), and imgC(R) are separate image segments and those regions are converted into distorted image while maintaining other segments of the image unchanged).
Sakamoto doesn’t disclose about the following limitation as further recited in the claim.
Fu discloses about comparing the image to the processed image to provide a comparison result (Fu in [Page – 4, Paragraph – 8] discloses, “The loss calculation function is used to process the de-distorted image, and the difference between the multi-scale de-distorted image and the multi-scale original image sample”).
It would have been obvious to one with one having an ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Fu into the system of Sakamoto because it would allow the system to accurately determine distortions even on curved or misaligned objects.
Sakamoto and Fu in the combination doesn’t disclose about the following limitation as further recited in the claim.
Phillipp discloses detecting one or more object defects based on the comparison result (Phillipp in [0009] discloses, “The method further includes generating a high-resolution output image by performing a method that includes overlaying the plurality of grayscale images over the color image, and correcting motion distortion of one or more objects detected in the grayscale images”).
It would have been obvious to one with one having an ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Phillipp into the system of Sakamoto in view of Fu because it would allow the system to efficiently correct the distortion of objects in image.
Summary of Citations (Sakamoto)
Paragraph [0027]; “the data acquirer 111 stores image data of a captured image received (or input) from an external device in the storage 150 as the captured image 151”.
Paragraph [0028 - 0029]; “The image corrector 112 generates an image (hereinafter referred to as an equivalent image because distortion has been corrected ... The object detector 113 detects a target object from an equivalent image generated by the image corrector 112 ”.
Paragraph [0035]; “When a captured image in which predetermined distortion has been generated is input according to machine learning, the learning model generator 116 generates a learning model which outputs a result obtained by identifying an object included in the captured image. The learning model generator 116 generates a learning model on the basis of the captured image 151 and the second teacher data 155 stored in the storage 150”.
Paragraph [0060]; “The second teacher data generator 115 converts the framed equivalent images imgC(L), imgC(C), imgC(R) into distorted images imgD(L), imgD(C) and imgD(R) having predetermined distortion to generate second teacher data. The learning model generator 116 generates a first learning model on the basis of the distorted image imgD(L), generates a second learning model on the basis of the distorted image imgD(C) and generates a third learning model on the basis of the distorted image imgD(R)”.
Summary of Citations (Fu)
[Page – 4, Paragraph – 8]; “The loss calculation function is used to process the de-distorted image, and the difference between the multi-scale de-distorted image and the multi-scale original image sample”.
Summary of Citations (Phillipp)
Paragraph [0009]; “The method further includes generating a high-resolution output image by performing a method that includes overlaying the plurality of grayscale images over the color image, and correcting motion distortion of one or more objects detected in the grayscale images”.
Regarding claim 5, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 1, and Sakamoto teaches claim 5 for the same grounds of rejection from the Non-Final Office Action of 07/09/2025.
Regarding claim 10, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 1, and Phillipp teaches claim 10 for the same grounds of rejection from the Non-Final Office Action of 07/09/2025.
Regarding claim 11, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 1, and Sakamoto teaches claim 11 for the same grounds of rejection from the Non-Final Office Action of 07/09/2025.
Regarding claim 12, is a non-transitory computer readable storage medium claim
corresponds to method claim 1. Therefore, the rejection analysis and motivation to combine of claim 1 is applicable to claim 12.
Regarding claim 17, is a non-transitory computer readable storage medium claim
corresponds to method claim 10. Therefore, the rejection analysis and motivation to combine of claim 10 is applicable to claim 17.
Regarding claim 18, is a non-transitory computer readable storage medium claim
corresponds to method claim 11. Therefore, the rejection analysis and motivation to combine of claim 11 is applicable to claim 18.
Regarding claim 19, apparatus claim 19 corresponds to method claim 1. Therefore, the rejection analysis and motivation to combine of claim 1 is applicable to claim 19.
Claim 3 is rejected under 35 U.S.C 103 as being unpatentable over Sakamoto in view of Fu and Phillipp and further in view of Richter US Patent Application Publication No. US-20190209116-A1 (hereinafter Richter).
Regarding claim 3, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 1 but fails to teach the further limitations as recited in claim 3. Richter teaches claim 3 for the same grounds of rejection and motivation established in the Non-Final Office Action of 07/09/2025.
Claim 4 is rejected under 35 U.S.C 103 as being unpatentable over Sakamoto in view of Fu and Phillipp and further in view of Zhu Patent Application Publication No. WO-2022006556-A1 (hereinafter Zhu).
Regarding claim 4, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 1 but fails to teach the further limitations as recited in claim 4. Zhu teaches claim 4 for the same grounds of rejection and motivation established in the Non-Final Office Action of 07/09/2025.
Claim 6 is rejected under 35 U.S.C 103 as being unpatentable over Sakamoto in view of Fu and Phillipp and further in view of Hu Patent Application Publication No. CN-109191476-A (hereinafter Hu).
Regarding claim 6, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 1 but fails to teach the further limitations as recited in claim 6. Hu teaches claim 6 for the same grounds of rejection and motivation established in the Non-Final Office Action of 07/09/2025.
Claims 7 and 14 are rejected under 35 U.S.C 103 as being unpatentable over Sakamoto in view of Fu and Phillipp and further in view of Cheng Patent Publication No. US-11615522-B1 (hereinafter Cheng).
Regarding claim 7, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 1 but fails to teach the further limitations as recited in claim 7. Cheng teaches claim 7 for the same grounds of rejection and motivation established in the Non-Final Office Action of 07/09/2025.
Regarding claim 14, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 12 but fails to teach the further limitations as recited in claim 14. Cheng teaches claim 14 for the same grounds of rejection and motivation established in the Non-Final Office Action of 07/09/2025.
Claims 8, 9, 15 and 16 are rejected under 35 U.S.C 103 as being unpatentable over Sakamoto in view of Fu and Phillipp and further in view of Lim Patent Application Publication No. CN-104870984-A (hereinafter Lim).
Regarding claims 8 and 9, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 1 but fails to teach the further limitations as recited in claims 8 and 9. Lim teaches claims 8 and 9 for the same grounds of rejection and motivation established in the Non-Final Office Action of 07/09/2025.
Regarding claims 15 and 16, the combination of Sakamoto, Fu and Phillipp as a whole teaches claim 12 but fails to teach the further limitations as recited in claims 15 and 16. Lim teaches claims 15 and 16 for the same grounds of rejection and motivation established in the Non-Final Office Action of 07/09/2025.
Claims 20 and 21 are rejected under 35 U.S.C 103 as being unpatentable over Sakamoto in view of Fu and Phillipp and further in view of Hefny Patent Application Publication No. KR-20210010517-A (hereinafter Hefny).
Regarding claim 20, Sakamoto in the combination discloses the method according to claim 1.
Sakamoto, Fu and Phillip in the combination doesn’t disclose about the following limitation as further recited in the claim.
Hefny discloses at least one image of at least one reference object was taken from a first point of view (Hefny in [0050] discloses, “Determining the face position may include receiving a video comprising a plurality of frames, which video is captured by a physical camera (eg, a camera within device 104) to a first viewpoint ... Determining the face position may also include detecting a face within the video, where the face is within a foreground portion of one or more frames of the video” wherein face is the reference object), and wherein at least one distorted segment is taken from a second point of view that differs from the first point of view (Hefny in [0006] discloses “determining a foreground portion of the plurality of frames ... positioning the virtual camera to a second view different from the first view ... a projection matrix of a foreground portion based on a virtual camera-the projection matrix corresponds to a second viewpoint-and generating a modified video including a modified foreground portion based on the projection matrix”. Furthermore, Hefny in [0040] also discloses about distorted segment (foreground portion), “In addition to distortion of foreground portions of the images (eg, a posture captured at an angle that can produce a lower quality video 304), the camera angle can also cause a distorted background 306”).
It would have been obvious to one with one having an ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Hefny into the system of Sakamoto in view of Fu and Phillip because the system would be able to perform better in correcting distortion caused by viewpoint change by teaching the ML model about distortion cause by camera viewpoint change.
Summary of Citations (Hefny)
Paragraph [0006]; “determining a foreground portion of the plurality of frames ... positioning the virtual camera to a second view different from the first view ... a projection matrix of a foreground portion based on a virtual camera-the projection matrix corresponds to a second viewpoint-and generating a modified video including a modified foreground portion based on the projection matrix”.
Paragraph [0040]; “In addition to distortion of foreground portions of the images (eg, a posture captured at an angle that can produce a lower quality video 304), the camera angle can also cause a distorted background 306”.
Paragraph [0050]; “Determining the face position may include receiving a video comprising a plurality of frames, which video is captured by a physical camera (eg, a camera within device 104) to a first viewpoint ... Determining the face position may also include detecting a face within the video, where the face is within a foreground portion of one or more frames of the video”.
Regarding claim 21, is a non-transitory computer readable storage medium claim
corresponds to method claim 20. Therefore, the rejection analysis and motivation to combine of claim 20 is applicable to claim 21.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZAID MUHAMMAD SALEH whose telephone number is (703)756-1684. The examiner can normally be reached M-F 8 am - 5 pm ET.
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 on (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.
/ZAID MUHAMMAD SALEH/
Examiner, Art Unit 2668
5/04/2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights