DETAILED ACTION
Notice of AIA Status
1. 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
2. Applicant’s remarks received on 03/20/2026 with respect to the original independent claims have been acknowledged but not found persuasive. Currently claims 1-20 are rejected.
With respect to the original independent claims, Applicant argues that just because Hong is not providing multiple trained models, it should not be relied upon for construction of prima facie case of obviousness. Examiner respectfully disagrees. The claimed plurality of trained models are used to classify images into different categories. They may be similar machine learning model structures trained on different labeled image corpuses, which causes each model to recognize different features. Although Hong does not literally state “plurality of models” Hong clearly produces the same results as the claimed invention by showing in fig. 4 multiple defect categories such as M line, bubble, unstretched, whiteness, and etc. Hong’s disclosure on multiple layers for different defect types is equivalent to claimed separate models for separate defect classes. Hong could have made the claimed limitation obvious by itself. For purpose of a compact prosecution Bakhshmand was added to show multiple models could be used to classify different defect types for reaching the same result. Therefore, the combined teaching would have made a prima facie case of obviousness on alternatives for producing expected result.
Response to Amendment
Claim Rejections - 35 USC § 103
3. 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 of this title, 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.
41066.. Claims 1-6, and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Hong et al (US Pub: 2020/0104993) and in further view of Bakhshmand et al (WO Pub: 2022/160040).
Regarding claim 1 (original), Hong et al teaches: A manufacturing apparatus configured to produce a processed article, the manufacturing apparatus having a defect detection system [abstract] comprising: a testing locus of the manufacturing apparatus staged at a known phase of manufacture of the processed article [p0058, p0059]; a sensor mount in proximity of the testing locus, the sensor mount visually unobstructed to the testing locus; a camera coupled to the sensor mount and oriented toward the testing locus [p0012, p0013, p0041, p0042, p0047 (The camera is placed to see the product at each step.)], the camera configured to generate image data [p0065]; a processor in data communication with the camera [p0066, p0082, fig. 2]; and a memory in data communication with the processor [p0083], each of the training images depicting a processed article at the known phase of manufacture [p0013], each of the models used to classify the image data into a plurality of categories, the categories comprising at least a defective presentation and a satisfactory presentation [p0062, p0066], and wherein the processor is configured to generate a classification result for the processed article indicating whether the processed article comprises a detected defect based upon classification of the image data generated by the camera into one of the plurality of categories [p0069].
Hong et al’s disclosure on multiple layers for different defect types is equivalent to claimed separate models for separate defect classes as Hong et al clearly produces the same results as the claimed invention by showing in fig. 4 multiple defect categories such as M line, bubble, unstretched, whiteness, and etc. For purpose of a compact prosecution Bakhshmand, in the same field of endeavor, is introduced to show multiple models could be used to classify different defect types for reaching the same result.
Bakhshmand et al teaches: wherein the memory comprises a plurality of trained models, each of the trained models trained using a corpus of training images [p0184-p0187]. Bakhshmand et al further teaches: wherein the processor is operable to add to the training corpus the image data generated by the camera and retrain the associated models utilizing the updated training corpus [p0286, p0287]. Therefore, given Bakhshmand et al’s prescription on multiple trained models using corpus of training images and updating training corpus to retrain the models, it would have been obvious for an ordinary skilled in the art before the effective filing date of the claimed invention to combine the teaching of the two to update training corpus to retrain models to identify new defect type for improving detection result.
Regarding claim 2 (original), the rationale applied to the rejection of claim 1 has been incorporated herein. Bakhshmand et al further teaches: The manufacturing apparatus of claim 1, further comprising a human-machine interface, and wherein the memory is configured to permit a user to update the training corpus and retrain the plurality of trained models via the human-machine interface [p0128].
Regarding claim 3 (original), the rationale applied to the rejection of claim 1 has been incorporated herein. Hong et al further teaches: The manufacturing apparatus of claim 1, wherein the plurality of categories comprise at least a first defective presentation correlated to a first defective condition of the processed article, a second defective presentation corresponding to a second defective condition of the processed article, and a satisfactory presentation corresponding to a condition of the processed article that does not comprise a visually-detectable defect [p0053-p0058, p0076, fig. 6].
Regarding claim 4 (original), the rationale applied to the rejection of claim 1 has been incorporated herein. Bakhshmand et al further teaches: The manufacturing apparatus of claim 1, wherein the processor delivers the classification result to a second processor associated with the manufacturing apparatus [p0292 (second processor for certainty check)].
Regarding claim 5 (original), the rationale applied to the rejection of claim 1 has been incorporated herein. Bakhshmand et al further teaches: The manufacturing apparatus of claim 1, wherein the processor is further operable to detect flaws of the processed article presented in the image data generated by the camera that are visually represented in the image data in an area of 1x1 square pixels or larger [p0152, p0250].
Regarding claim 6 (original), the rationale applied to the rejection of claim 1 has been incorporated herein. Hong et al further teaches: The manufacturing apparatus of claim 1, wherein the camera comprises a color camera and the image data generated by the camera comprises color data [p0010].
Regarding claim 8 (original), the rationale applied to the rejection of claim 1 has been incorporated herein. Bakhshmand et al further teaches: The manufacturing apparatus of claim 1, wherein the image data resolution conforms to at least a 320p video standard [p0272].
51066.. Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Hong et al (US Pub: 2020/0104993) and Bakhshmand et al (WO Pub: 2022/160040); and in further view of Gissibl et al (Two-photon direct laser writing of ultracompact multi-lens objectives, 6/27/2016).
Regarding claim 7 (original), the rationale applied to the rejection of claim 1 has been incorporated herein. Hong et al in view of Bakhshmand et al does not disclose an additive manufacturing technique for camera. In the same field of endeavor, Gissibl et al teaches: The manufacturing apparatus of claim 1, wherein the camera is assembled using an additive manufacturing technique [page 1]. Therefore, given Gissibl et al’s prescription on additive manufacturing for fabricating multi-lens optical system for camera, it would have been obvious for an ordinary skilled in the art before the effective filing date of the claimed invention to combine the teaching of all to apply camera with additive manufacturing technique for improving imaging capability.
61066.. Claims 9-18 are rejected under 35 U.S.C. 103 as being unpatentable over Hong et al (US Pub: 2020/0104993) and Bakhshmand et al (WO Pub: 2022/160040); and in further view of Tang et al (US Pub: 2021/0209414).
Claims 9 (currently amended) has been analyzed and rejected with regard to claims 1. Hong et al in view of Bakhshmand et al does not explicitly associate a model closely correlating to image data. In the same field of endeavor, Tang et al teaches: retraining the plurality of trained models by associating the image data with the trained model with which it most closely correlates [p0041]. Notice, known categories for plurality of classification would have been inherent feature of ML models for predefined features. Therefore, it would have been obvious for an ordinary skilled in the art before the effective filing date of the claimed invention to combine the teaching of the all to have models associated with different image data based on defect types for more accurate detection.
Regarding claims 10-13 (original), the rationale applied to the rejection of claim 9 has been incorporated herein. Claims 10-13 have been analyzed and rejected with regard to claims 3, 5, 6, and 8 respectively.
Regarding claim 14 (original), the rationale applied to the rejection of claim 9 has been incorporated herein. Bakhshmand et al further teaches: The method of claim 9, further comprising generating a second classification result for the processed article when the correlation of the image data with a trained model other than the most-closely correlated comprises a correlation value above a threshold value [p0185, p0260-p0265].
Regarding claim 15 (original), the rationale applied to the rejection of claim 14 has been incorporated herein. Bakhshmand et al further teaches: The method of claim 14, further comprising generating additional classification results for the processed article for each correlation of the image data with a trained model that comprises a correlation value above the threshold value [p0169, p0260 (Double check when labeled/classified as defect.)].
Claim 16 (original) has been analyzed and rejected with regard to claim 9 for repeated process in accordance with Bakhshmand et al’s further teaching on advancing to different stage of manufacturing process [p0002, p0003] and Tang et al’s disclosure on classification training model alignment with closely correlated image data.
Regarding claims 17 and 18 (original), the rationale applied to the rejection of claim 16 has been incorporated herein. Claims 17 and 18 have been analyzed and rejected with regard to claims 14 and 15 respectively.
71066.. Claims 19 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Hong et al (US Pub: 2020/0104993), Bakhshmand et al (WO Pub: 2022/160040), and Tang et al (US Pub: 2021/0209414); and in further view of Yankov et al (US Pub: 2012/0095943).
Claim 19 (currently amended) has been analyzed and rejected with regard to claim 9 and in accordance with Hong et al’s teaching on: A non-transitory computer-readable medium having stored thereon instructions that, when executed by a processor, cause the processor to perform the steps [p0083].
In the same field of endeavor, Yankov et al further teaches a plurality of separate category specific classifiers and per classifier scoring/threshold selection, adding labeled examples to a training set , and retraining the plurality of classifiers: Generating at least one classification label for the processed article based upon a correlation result between the image data and each of the trained models, each classification label aligning classifications of the trained model or models in the corpus with which the image data most closely correlates; adding the image data to the corpus; and retraining the plurality of trained models by associating the image data with the trained model with each model with which it correlates above a threshold value [abstract, p0033, p0041, p0100-p0102]. Therefore, it would have been obvious for an ordinary skilled in the art to combine the teaching of all to classify newly captured inspection images using category specific models to improve automated defect detection.
Regarding claim 20 (original), the rationale applied to the rejection of claim 19 has been incorporated herein. Claim 20 has been analyzed and rejected with regard to claim 16
Conclusion
8. There is a new ground of rejection necessitated by the corresponding amendment 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 extension fee 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
9. Any inquiry concerning this communication or earlier communications from the examiner should be directed to FAN ZHANG whose telephone number is (571)270-3751. The examiner can normally be reached on Mon-Fri 9:00-5:00.
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, Benny Tieu can be reached on 571-272-7490. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Fan Zhang/
Patent Examiner, Art Unit 2682
Prosecution Insights