DETAILED ACTION
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 .
Response to Arguments
Applicant’s arguments with respect to independent claims 1, 8, and 15 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 2, 3, 6, 7, 8-10, 13, 14; 15-17 and 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Cole (US 20250022184 A1).
Claim 1
In regards to claim 1, Cole discloses a processor, comprising: one or more circuits to cause one or more neural networks {see cites below including machine learning model 318. As to processor, see Fig. 1 processor 104 and Fig. 12 processor 1204 connected to storage device storing applications 1212 (computer program instructions) executing on processor 1204, [0085]-[0094]} to
identify one or more three-dimensional (3D) positions of at least one portion of one or more portions of one or more objects
{Figs. 10, 11 including estimating 3D pose 1108 from a captured image of a scene using a machine learning model 318 wherein the model is trained (316) using processed training target images 910, [0070]-[0076], [0080]-[0083]. Note that the BRI of “position” includes poses as per [0059] of the instant published application.}
based, at least in part, on: occluding different portions of the one or more objects in a plurality of different images of the one or more objects to cause different 3D positions of the one or more objects in the plurality of different images to be visible to update the one or more neural networks
{Fig. 7 (copied below) including cropping operation 706 that crops/occludes different portions of the object(s) to cause different 3D positions of the one or more objects in the plurality of different images to be visible to update the one or more neural networks, [0050]-[0058]. See also Fig. 3, training target data generation 312 which uses the occluded/cropped training data set to train the object pose determination network, [0034]-[0036], [0048]
PNG
media_image1.png
472
852
media_image1.png
Greyscale
}
Claim 2
In regards to claim 2, Cole discloses wherein the one or more circuits are to cause at least a portion of the plurality of different images to be truncated {see mapping for claim 1 wherein a portion of the images are truncated via cropping operation 706. It is further noted that the instant specification uses the terms cropped and truncated synonymously thus even more clearly bringing this disclosure within the BRI}.
Claim 3
In regards to claim 3, Cole discloses wherein the portion of truncated images are used to train the one or more neural networks {see mapping of claim 1 wherein the cropped/truncated images are used to train the neural network}.
Claim 6
In regards to claim 6, Cole discloses wherein the one or more circuits are further to identify the one or more 3D positions based, at least in part, on ground truth data associated with the plurality of different images {see mapping of claim 1. See also [0017], [0031], [0058], [0058]}.
Claim 7
In regards to claim 7, Cole discloses wherein the one or more circuits are to cause at least some of the ground truth data to be truncated {see mapping of claim 1 including in which the original full image is cropped/truncated to create training data}.
Claims 8-10, 13, 14; 15-17 and 20
The rejection of processor claims 1, 2, 3, 6, and 7 above applies mutatis mutandis to the corresponding limitations of method claims 8, 9, 10, 13 and 14. Also, the rejection of processor claims 1, 2, 3, and 6 above applies mutatis mutandis to the corresponding limitations of system claims 15, 16, 17, and 20 while noting that the rejection above cites to both device and method disclosures.
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.
Claim 4, 5, 11, 12, 18, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Cole and Mckenzie {McKenzie, Elizabeth M., et al. "Using neural networks to extend cropped medical images for deformable registration among images with differing scan extents." Medical physics 48.8 (2021): 4459-4471}.
Claim 4
In regards to claim 4, Cole discloses wherein the portion of the plurality of different images are truncated based, at least in part, on a generated value
Mckenzie is analogous art from the same field of creating neural network training data using cropped images. In more detail, McKenizie teaches determining missing anatomy caused by portions of the object (human body) being occluded in the image(s) via a missing/occluded anatomy synthesis process which is based, at least in part, on a neural network trained with images in which portion(s) are occluded (cropped images) and second images in which the portion(s) are not occluded (original full images). See Abstract, Methods, Conclusions, Sections 1, 2. Note that Mckenzie solves the same problem as the instant invention which creating training data to deal with occlusions due to an object being partially out of fame. Compare instant spec’s [0059]-[0060] with McKenzie’s Abstract, Section 1. Also note that the instant spec includes generative adversarial networks (GAN) in [0545] thus further aligning Mckenzie’s generative adversarial network (CropGAN) with the claimed invention’s BRI (broadest reasonable interpretation}.
Mckenzie also teaches wherein the portion of the one or more second images are truncated based, at least in part, on a generated value satisfying a threshold
{see section 2.2 in which the training (second) image is truncated based on a randomly varied number (cropping angle) that satisfying a threshold (varied between 0 and 45 degrees in superior-inferior cropping angle and between -5 and 5 degrees in the other two dimensions)}.
It 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 to have modified Cole which already discloses wherein the portion of the one or more second images are truncated based, at least in part, on a generated value such that the generated value also satisfies a threshold as taught by McKenzie, because McKenzie motivates doing so in order to vary the cut angle of the crop to simulate common real world scenarios in section 2.2, because there is a reasonable expectation of success and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claim 5
In regards to claim 5, Cole discloses wherein an amount by which the portion of the plurality of different images are to be truncated is based, at least in part, on a generated value
McKenzie also teaches wherein an amount by which the portion of the one or more second images are to be truncated is based, at least in part, on a generated value satisfying one or more thresholds
{see section 2.2 in which the training (second) image is truncated by an amount based on a randomly varied number (cropping angle) that satisfying a threshold (varied between 0 and 45 degrees in superior-inferior cropping angle and between -5 and 5 degrees in the other two dimensions}.
It 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 to have modified Cole which already discloses wherein the portion of the one or more second images are truncated based, at least in part, on a generated value such that the generated value also satisfies a threshold and wherein an amount by which the portion of the one or more second images are to be truncated is based, at least in part, on a generated value satisfying one or more thresholds as taught by McKenzie, because McKenzie motivates doing so in order to vary the cut angle of the crop to simulate common real world scenarios in section 2.2, because there is a reasonable expectation of success and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claims 11, 12; 18, 19
The rejection of processor claims 4 and 5 above applies mutatis mutandis to the corresponding limitations of method claims 11 and 12. Also, the rejection of processor claims 4 and 5 above applies mutatis mutandis to the corresponding limitations of system claims 18 and 19 while noting that the rejection above cites to both device and method disclosures.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
W. Wan, A. Walsman and D. Fox, "Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks," 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 2019, pp. 4882-4888, doi: 10.1109/ICRA.2019.8793656 discloses a data augmentation that augments neural network training with cropped/truncated data and original full images and augmenting the dataset by overlaying different objects to control the trained occlusion amount of the person being imaged.
Yuille US 20240290075 A1 discloses a neural network for object detection in which at least part of the object is occluded including training images which are cropped. See [0056]-[0059].
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael R Cammarata whose telephone number is (571)272-0113. The examiner can normally be reached M-Th 7am-5pm EST.
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, Matthew Bella can be reached at 571-272-7778. 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.
/MICHAEL ROBERT CAMMARATA/Primary Examiner, Art Unit 2667
Prosecution Insights