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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 02/26/2026 has been entered.
Status of Claims
Claims 1-3, 6-13, and 16-17 are pending. Claims 4-5 and 14-15 are canceled.
Response to Arguments
Applicant’s arguments, see p.6-8, filed 02/12/2026, with respect to the rejections of Claims 1-3, 6-13, and 16-17 under 35 U.S.C. 103 have been fully considered but are moot because Applicant’s amendments have altered the scope of the claims, and therefore, necessitated new grounds of rejection which are presented below.
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.
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 1-3, 6-13, and 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over Nozaki et al. (US 11024031 B1) in view of Okuda (US 20170069075 A1), Santamaria-Pang et al. (US 11301977 B2), and Niculescu-Mizil et al. (US 20180374569 A1).
Regarding Claim 1, Nozaki teaches "An index selection device comprising: a hardware processor that calculates abnormality scores of a non-defective product and a defective product by using a plurality of indices based on a plurality of pieces of input data of the non-defective product and the defective product and a plurality of pieces of reference data corresponding to the input data"; (Nozaki, Abstract and Col. 3 lines 21-42 and Col. 10 lines 32-43, teaches a system including a processor that compares subject images of a stomach with reference images of a healthy stomach and different severity levels of gastric conditions wherein subject image abnormality scores are calculated for differences between the subject image data and the reference image data and wherein the scores are calculated based on projection deviation, single pixel 2D deviation, or single voxel 3D deviation, i.e., a processor that calculates abnormality scores of the non-defective product and the defective product by using a plurality of indices of the input data being the image data of the non-defective product and the defective product and the reference image data corresponding to the input data).
However, Nozaki does not explicitly teach "and selects any one of the plurality of indices according to the abnormality scores of the non-defective product and the defective product; wherein the hardware processor selects any one of the plurality of indices using a model trained so as to maximize a difference between a distribution of the abnormality score of the non- defective product and a distribution of the abnormality score of the defective product as an objective variable with feature amounts of the plurality of pieces of input data of the non- defective product and the defective product as explanatory variables; wherein the hardware processor generates reconstructed data as the reference data based on input data of a plurality of non-defective products by a generative model trained using the input data of the plurality of non-defective products; and wherein the reconstructed data includes only essential elements to determine the feature amounts”.
In an analogous field of endeavor, Okuda teaches "and selects any one of the plurality of indices according to the abnormality scores of the non-defective product and the defective product"; (Okuda, Claims 1 and 8, teaches a selection unit which selects a feature amount for determining whether a target object is defective or non-defective from among the extracted feature amounts wherein the selection unit calculates a score including a number of feature amounts for determining whether the target object is defective or non-defective, i.e., select any one of the plurality of indices according to the abnormality scores of the defect and non-defective product);
"wherein the hardware processor selects any one of the plurality of indices using a model trained so as to maximize a difference between a distribution of the abnormality score of the non- defective product and a distribution of the abnormality score of the defective product as an objective variable with feature amounts of the plurality of pieces of input data of the non- defective product and the defective product as explanatory variables"; (Okuda, Paras. 5,6 and 78-80, teaches a classifier for classifying non-defective and defective products in a multidimensional feature amount space that uses learning samples and a learning period, i.e., a trained model, and that selects feature amounts from a plurality of extracted feature amounts and determining if the target object is non-defective or defective based on the selected feature amount wherein the feature amount includes a maximum value and wherein feature amounts are sorted and scored in an order from a smallest evaluation value in which the feature amount selection unit arranges the objects in the order of the scores for each of the feature amounts used in which an area under a ROC curve can be used as the separation degree of data to acquire the highest evaluation value, i.e., select the index with a difference between a maximum or highest difference between the score of the non-defective product and a defective product as the objective variable wherein the feature amounts are explanatory variables of the maximized difference for the score objective).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Nozaki by including the selection of product indices according to a score for the defective and non-defective products taught by Okuda. One of ordinary skill in the art would be motivated to combine the references since allows for easy labeling of products and reduces the amount of learning required (Okuda, Para. 112, teaches the motivation of combination to be to reduce the number of times of learning and inspection and easily label products).
However, the combination of references of Nozaki in view of Okuda does not explicitly teach “wherein the hardware processor generates reconstructed data as the reference data based on input data of a plurality of non-defective products by a generative model trained using the input data of the plurality of non-defective products; and wherein the reconstructed data includes only essential elements to determine the feature amounts”.
In an analogous field of endeavor, Santamaria-Pang teaches "wherein the hardware processor generates reconstructed data as the reference data based on input data of a plurality of non-defective products by a generative model trained using the input data of the plurality of non-defective products"; (Santamaria-Pang, Col. 3 lines 22-39 and Col. 10 lines 35-45, teaches using sample input images and normal data derived from the sample images that do not contain defects to reconstruct an input image of a component to be inspected that is then compared with the input image wherein a processor employs a deep learning neural network, i.e., a hardware processor that generates reconstructed data as reference data based on an input of non-defective products by a generative model trained using the input data of the non-defective products).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Nozaki and Okuda by including the generation of reconstructed data to be used as reference data by a generative model taught by Santamaria-Pang. One of ordinary skill in the art would be motivated to combine the references since it does not require a large quantity of samples and improves detection efficiency (Santamaria-Pang, Col. 1 lines 30-33, teaches the motivation of combination to be to train inspection systems without a large quantity of defective samples while improving efficiency of detection).
However, the combination of references of Nozaki in view of Okuda and Santamaria-Pang does not explicitly teach "and wherein the reconstructed data includes only essential elements to determine the feature amounts".
In an analogous field of endeavor, Niculescu-Mizil teaches "and wherein the reconstructed data includes only essential elements to determine the feature amounts"; (Niculescu-Mizil, Paras. 18-19, 32, 35-36, and 47, teaches the reconstructor including an encoder-decoder arrangement deployed to reconstruct images of a product containing defects wherein the reconstructor will reconstruct the image to remove any defects or anomalies and therefore generate the reconstructed image as a representation of the item that has no defects or anomalies and wherein the decoder is trained to predict defectless features so that the predicted image portion including a reconstructed image patch having no defects or anomalies even if the corresponding image patch of the original image did have defects or anomalies and wherein an anomaly is considered to be a feature of the item depicted in the image which can be tagged as different from the defectless item as a potential anomaly or defect, i.e., the reconstructed data as the reconstructed image includes only essential elements being the defectless features to determine the feature amounts being the presence of anomalies or defects through the detection and tagging of those features).
It would have been obvious to one having ordinary skill in the art before the effective filing date to modify the invention of Nozaki, Okuda, and Santamaria-Pang by including the reconstructed data only including the essential elements to determine the feature amounts taught by Niculescu-Mizil. One of ordinary skill in the art would be motivated to combine the references since it reduces complexity of reconstruction and improves speed and efficiency of the system (Niculescu-Mizil, Para. 43, teaches the motivation of combination to be to reduce complexity of reconstruction and improve the speed and efficiency of an anomaly detection and tagging system).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date.
Regarding Claim 2, the combination of references of Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil teaches "The index selection device according to claim 1, wherein the abnormality scores are differences between results of calculating the indices using the input data and results of calculating the indices using the reference data for each of the non-defective product and the defective product"; (Nozaki, Col. 3 lines 21-42 and Col. 10 lines 32-43, teaches the abnormality scores being indicative of an array of structural deviations of the subject relevant to the reference image data wherein the reference image data includes healthy and different severity levels of gastric conditions, i.e., abnormality scores are differences between the calculated indices using the input data and reference data for defective and non-defective products being the healthy and unhealthy stomachs).
Regarding Claim 3, the combination of references of Nozaki in view of Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil teaches "The index selection device according to claim 1, wherein the hardware processor selects an index with which a difference between a distribution of the abnormality score of the non-defective product and a distribution of the abnormality score of the defective product with respect to the plurality of pieces of input data and the plurality of pieces of reference data is maximized"; (Okuda, Paras. 5,6 and 78-80, teaches selecting feature amounts from a plurality of extracted feature amounts and determining if the target object is non-defective or defective based on the selected feature amount wherein the feature amount includes a maximum value and wherein feature amounts are sorted and scored in an order from a smallest evaluation value in which the feature amount selection unit arranges the objects in the order of the scores for each of the feature amounts used in which an area under a ROC curve can be used as the separation degree of data to acquire the highest evaluation value, i.e., select the index with a difference between a maximum or highest difference between the score of the non-defective product and a defective product with respect to the input and reference data).
The proposed combination as well as the motivation for combining the Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil references presented in the rejection of Claim 1, applies to claim 3. Thus, the device recited in claim 3 is met by Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil.
Regarding Claim 6, the combination of references of Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil teaches "The index selection device according to claim 1, wherein the input data is color image data, and the hardware processor calculates the abnormality scores based on hues and/or saturation as the indices"; (Nozaki, Col. 27 lines 7-23, Col. 29 lines 63-67, and Col. 30 lines 1-9, teaches input data being color images wherein the abnormality scores are calculated based on difference between saturation of the contrast areas and amount of luminance measured by color converting the image to extract only green, i.e., calculate abnormality score based on hues and/or saturation as the indices).
Regarding Claim 7, the combination of references of Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil teaches "An information processing device comprising: an hardware processor that acquires input data, and calculates an abnormality score based on the input data acquired by the hardware processor, reference data corresponding to the input data, and the index selected by the index selection device according to claim 1"; (Okuda, Paras. 37-39 and 120 and Claims 1 and 8, teaches a processor that includes an image acquisition unit that acquires an image from the imaging apparatus and an image composition unit for learning target images wherein a selection unit which selects a feature amount for determining whether a target object is defective or non-defective from among the extracted feature amounts wherein the selection unit calculates a score including a number of feature amounts for determining whether the target object is defective or non-defective, i.e., calculate an abnormality score based on the input data, reference data, and selected index or feature amount).
The proposed combination as well as the motivation for combining the Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil references presented in the rejection of Claim 1, applies to claim 7. Thus, the device recited in claim 7 is met by Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil.
Regarding Claim 8, the combination of references of Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil teaches "An inspection device comprising a hardware processor that determines a non-defective product or a defective product based on the abnormality score output by the information processing device according to claim 7"; (Okuda, Claim 8, teaches the selection unit calculating a score including a number of feature amounts for determining whether the target object is defective or non-defective, i.e., determining a product as defective or non-defective based on the score output).
The proposed combination as well as the motivation for combining the Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil references presented in the rejection of Claim 1, applies to claim 8. Thus, the device recited in claim 8 is met by Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil.
Regarding Claim 9, the combination of references of Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil teaches "An information processing system comprising: the information processing device according to claim 7; and a display device that displays the abnormality score calculated by the hardware processor"; (Nozaki, Col. 20 lines 21-29, teaches outputting the abnormality score to the user via an output device such as a display, i.e., a display device that display the abnormality score calculated).
Regarding Claim 10, the combination of references of Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil teaches "An inspection system comprising: the inspection device according to claim 8; and a display device that displays a result of the determination by the hardware processor"; (Nozaki, Col. 29 lines 8-20, teaches outputting the final results of the analysis to a display, i.e., a display device that displays a result of the determination).
Claim 11 recites a method with steps corresponding to the elements of the system recited in Claim 1. Therefore, the recited steps of this claim are mapped to the proposed combination in the same manner as the corresponding elements in its corresponding system claim. Additionally, the rationale and motivation to combine the Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil references, presented in rejection of Claim 1, apply to this claim.
Claim 12 recites a method with steps corresponding to the elements of the system recited in Claim 2. Therefore, the recited steps of this claim are mapped to the proposed combination in the same manner as the corresponding elements in its corresponding system claim. Additionally, the rationale and motivation to combine the Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil references, presented in rejection of Claim 1, apply to this claim.
Claim 13 recites a method with steps corresponding to the elements of the system recited in Claim 3. Therefore, the recited steps of this claim are mapped to the proposed combination in the same manner as the corresponding elements in its corresponding system claim. Additionally, the rationale and motivation to combine the Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil references, presented in rejection of Claim 1, apply to this claim.
Claim 16 recites a method with steps corresponding to the elements of the system recited in Claim 6. Therefore, the recited steps of this claim are mapped to the proposed combination in the same manner as the corresponding elements in its corresponding system claim. Additionally, the rationale and motivation to combine the Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil references, presented in rejection of Claim 1, apply to this claim.
Claim 17 recites a computer-readable storage medium storing a program with instructions corresponding to the steps recited in Claim 11. Therefore, the recited programming instructions of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of the Nozaki in view of Okuda, Santamaria-Pang, and Niculescu-Mizil references discloses a computer readable storage medium (for example, see Nozaki, Abstract).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREW STEVEN BUDISALICH whose telephone number is (703)756-5568. The examiner can normally be reached Monday - Friday 8:30am-5:00pm 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, Amandeep Saini can be reached on (571) 272-3382. 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.
/ANDREW S BUDISALICH/Examiner, Art Unit 2662
/AMANDEEP SAINI/Supervisory Patent Examiner, Art Unit 2662