DETAILED ACTION
This action is in response to the application filed on October 16th, 2024. Claims 1-20 are pending and have been examined.
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
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-4, 10-16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over “Catenary Insulator Defect Detection: A Dataset and an Unsupervised Baseline” (herein after referred to by its primary author, Zhang) in view of “Defect Detection in Computer Motherboard Assembly through Fusion of Multi-Scale Features and Attention Mechanisms” (herein after referred to by its primary author, Li).
In regards to claim 1, Zhang teaches a method comprising: receiving corrupted images of a Zhang Figure 5(b) “Inference”; Section IV B “After pretraining, we can obtain the reconstruction models, which will be used to complete the reconstruction task of test images in the inference phase” Examiner note: While Figure 5(b) shows an example where the test image is a defective input, it can be appreciated that, when performing inference with a model used to determine defects, it is unknown whether a test image contains a defect or not); generating an output image for each of the corrupted images by the trained model, which is configured to generate output images that are healthy estimate images (Zhang Figure 5(b) “Reconstruction”; Section IV A “As only normal images participate in the training process, the reconstructed images tend to be normal, resulting in smaller reconstruction errors for normal images and larger errors for anomaly images”); aggregating the output images into an aggregated image (Zhang Figure 7 “Combination”); comparing the aggregated image with the test image in a comparison (Zhang Figure 5(c) “SSIM”); generating a visual representation of the comparison, wherein the visual representation represents that the computing component is healthy or unhealthy (Zhang Figure 5(c) “Anomaly map”/“Visualization”).
Zhang does not teach receiving images of a computing component into a trained model.
However, Li teaches receiving images of a computing component into a trained model (Li Abstract “To meet the growing demands for automation and intelligence in the quality inspection of computer motherboard assembly, this study proposes an improved defect detection method based on RetinaNet.”).
Li is considered to be analogous to the claimed invention because they are both in the same field of motherboard defect detection. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the system of Zhang to include the teachings of Li, to provide the advantage of improved inspection efficiency (Li Section I “Implementing automated detection would significantly improve inspection efficiency during the assembly process, addressing the current limitations in quality control.”)
In regards to claim 2, Zhang in view of Li teaches the method of claim 1, wherein the computing component is unhealthy when a region of the visual representation represents a difference between the test image and the aggregated image that is greater than a difference between other regions of the test image and the aggregated image (Zhang Section IV D “In specific terms, for image-level evaluation, we determine the predicted value for each image by selecting the maximum value within the anomaly score map as the image-level probability of the image containing defects.”).
In regards to claim 3, Zhang in view of Li teaches the method of claim 2, further comprising corrupting the test image to generate the corrupted images, wherein each of the corrupted images is generated by placing a mask over a region of the test image, wherein the masked regions for each of the corrupted images is in a different location of the test image (Zhang Figure 7 “Interval mask”).
In regards to claim 4, Zhang in view of Li teaches the method of claim 3, wherein the aggregated image is an average of the output images (Zhang Figure 7 “Combination”; Section IV C “The final reconstructed image is then generated by combining the patches of the masked regions from both two reconstructed images.”).
In regards to claim 10, Zhang in view of Li teaches the method of claim 1, wherein the model is an inpainting model, and the model is trained from scratch using corrupted images generated only from healthy images such that the model is configured to fill areas corresponding to masks in the corrupted images with data corresponding to healthy images (Zhang Figure 5(a) “Defect-free input”; Section IV A “As only normal images participate in the training process, the reconstructed images tend to be normal, resulting in smaller reconstruction errors for normal images and larger errors for anomaly images.”).
In regards to claim 11, Zhang in view of Li teaches the method of claim 1, wherein the visual representation identifies anomalies in the computing component as regions having a higher pixel difference than other regions (Zhang Figure 5(c) “Anomaly Map”; Figure 8).
In regards to claim 12, Zhang in view of Li teaches the method of claim 1, further comprising generating the test image by photographing the computing component (Zhang Section IV C “In the inference phase, our goal is to detect defects in test images by masking the defect regions as much as possible and reconstructing the images without the defect.”).
In regards to claim 13, Zhang in view of Li renders obvious the claim limitations as in the consideration of claim 1.
In regards to claim 14, Zhang in view of Li renders obvious the claim limitations as in the consideration of claim 2.
In regards to claim 15, Zhang in view of Li renders obvious the claim limitations as in the consideration of claim 3.
In regards to claim 16, Zhang in view of Li renders obvious the claim limitations as in the consideration of claim 4.
In regards to claim 20, Zhang in view of Li renders obvious the claim limitations as in the consideration of claim 10.
Claims 5-9 and 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Li as applied to the claims above, and further in view of “Identifying Outliers, Defective Areas and Performance Evaluation of a PV Module using EL Image Processing: A Variational Autoencoder Approach” (herein after referred to by its primary author, Soumik).
In regards to claim 5, Zhang in view of Li teaches the method of claim 1, wherein the visual representation comprises a heatmap or an overlay of the heatmap with the test image (Zhang Figure 5(c) “Anomaly map”/“Visualization”) further comprising identifying one or more regions of interest in the visual representation having higher colors than other areas of the heatmap (Zhang Figure 8; Figure 8 Description “Detailed calculation flow about how to convert from a pixel-level similarity map to a defect score map. We consider the maximum value within the anomaly score map as the probability of the image containing defects to calculate the image-level metrics. In pixel-level evaluation, we utilize every pixel value as the probability of each pixel in the input image being defective. In the end, they are transformed into a binary classification problem to resolve the metrics.”).
Zhang in view of Li does not teach wherein differences identified in the comparison and represented in the heatmap are normalized.
However, Soumik teaches wherein differences identified in the comparison and represented in the heatmap are normalized (Soumik Figures 8(d), 8(e), 9(d), and 9(e)).
Soumik is considered to be analogous to the claimed invention because they are both in the same field of defect detection. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the system of Zhang in view of Li to include the teachings of Soumik, to provide the advantage of easy visual comprehension of the visualization representation (Soumik Section IV “The normalized Figure 9(e) offers clear insight into the intensity of defects or the impact of cracks, facilitating easy comprehension.”)
In regards to claim 6, Zhang in view of Li and Soumik teaches the method of claim 5, wherein the one or more regions of interest indicate that the computing component is unhealthy, wherein the computing component is deemed healthy when the region of interest is not present in the visual representation (Zhang Figure 5).
In regards to claim 7, Zhang in view of Li and Soumik teaches the method of claim 6, wherein the unhealthy status comprises a missing element of the computing component (Li Figure 4).
In regards to claim 8, Zhang in view of Li and Soumik teaches the method of claim 7, wherein the computing component comprises a motherboard (Li Abstract “To meet the growing demands for automation and intelligence in the quality inspection of computer motherboard assembly, this study proposes an improved defect detection method based on RetinaNet.”).
In regards to claim 9, Zhang in view of Li and Soumik teaches the method of claim 6, further comprising evaluating the computing component starting at locations corresponding to the one or more regions of interest (Zhang Figure 8).
In regards to claim 17, Zhang in view of Li and Soumik renders obvious the claim limitations as in the consideration of claims 5, 11, and 12.
In regards to claim 18, Zhang in view of Li and Soumik renders obvious the claim limitations as in the consideration of claims 6, 7, and 8.
In regards to claim 19, Zhang in view of Li and Soumik renders obvious the claim limitations as in the consideration of claim 9.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
“Synthetic Data Generation for Enhanced Visual Metal Defect Detection” teaches a method of creating defect images from a test image, and also teaches performing anomaly map normalization.
“Synthetic Data Generation for Steel Defect Detection and Classification Using Deep Learning” teaches a method of creating defect images from a test image, and visualizing the differences in a heat map.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CALEB LOGAN ESQUINO whose telephone number is (703)756-1462. The examiner can normally be reached M-Fr 8:00AM-4:00PM 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, Andrew Bee can be reached at (571) 270-5183. 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.
/CALEB L ESQUINO/ Examiner, Art Unit 2677
/ANDREW W BEE/ Supervisory Patent Examiner, Art Unit 2677
Prosecution Insights