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 .
Claim Objections
Claims 9 and 19 are objected to because of the following informalities:
“The method according to claim 1, wherein the determining comprises determining that two EMI patches representations are not indicative of a EMI defect when EMI patches representations scores if the two or more EMI patches representations are similar to each other” appears as if it should recite “The method according to claim 1, wherein the determining comprises determining that two EMI patches representations are not indicative of a EMI defect when EMI patches representations scores indicate that the two or more EMI patches representations are similar to each other.”
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The method of claim 1 is directed to a process, which is one of the statutory categories of invention, and passes Step 1: Statutory Category- MPEP § 2106.03. However, the following limitations of Claim 1 recite steps that can be performed in the human mind or with pen and paper, therefore failing Step 2A Prong One. These limitations constitute mental processes because they describe acts of observation, evaluation, and judgement that can practically be performed in the human mind, or by a human using pen and paper as a physical aid. Additionally, these limitations of claim 1 recite Mathematical Concepts, which are defined as mathematical relationships, mathematical formulas or equations, or mathematical calculations. The claim must recite (i.e. set forth or describe) a mathematical concept rather than include limitations that are merely based on math.
generating EMI patches representations that are related to the EMI; wherein the EMI patches representations of the EMI are selected out of (a) representations of patches of the image of the EMI, or (b) patches of a representation of the image of the EMI;
calculating EMI patches representations scores, wherein an EMI patch representation score of a certain EMI patch representation is determined based on similarities between the certain EMI patch representation and other EMI patch representations;
and determining a defect related status of the EMI based on at least some of the EMI patches representations scores and on at least one similarity related values.
Claim 1 fails Step 2A Prong Two because the additional elements beyond the judicial exception, including receiving an image of an evaluated manufactured item (EMI), do not integrate the judicial exception into a practical application. Receiving an image is insignificant pre-solution activity (MPEP 2106.05(g)), and limiting the abstract idea to manufactured items merely ties the idea to a particular technological environment and field of use (MPEP 2106.05(h)), thus applying the abstract idea on a computer (MPEP § 2106.05(f)). Claim 1 also fails Step 2B, as these additional elements are well-understood, routine, and conventional (WURC), adding nothing significantly more than the abstract idea itself (MPEP § 2106.07(a)((III)); receiving an image is WURC (see MPEP § 2106.05(d)). Claim 11 contains this identical ineligible subject matter, with the only additional element beyond the judicial exception being a processor. Therefore, it fails Step 2A Prong Two (see claim 1 analysis above) and Step 2B; a processor is a generic computer element that is WURC (see MPEP § 2106.05(d)).
Claims 2-10 recite steps that can be performed in the human mind or with pen and paper, therefore failing Step 2A Prong One. These limitations constitute mental processes because they describe acts of observation, evaluation, and judgement that can practically be performed in the human mind, or by
a human using pen and paper as a physical aid. Additionally, claims 4 and 5 recite Mathematical Concepts, which are defined as mathematical relationships, mathematical formulas or equations, or mathematical calculations. The claim must recite (i.e. set forth or describe) a mathematical concept rather than include limitations that are merely based on math. These claims fail Step 2A Prong Two and Step 2B because there are no additional elements beyond the judicial exception. As claims 12-20 contain this identical ineligible subject matter, they are also rejected.
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 1-20 are rejected under 35 U.S.C. 102 (a)(1) as being anticipated by Roth et. al (“Towards Total Recall in Industrial Anomaly Detection”).
Regarding Claim 1, Roth teaches a method for context-based detection of defects of manufactured items, the method comprises (Fig. 2 (shown below)):
PNG
media_image1.png
242
706
media_image1.png
Greyscale
receiving an image of an evaluated manufactured item (EMI), the EMI was manufactured by a manufacturing process;
4.1 Experimental Details: “To study industrial anomaly detection performance, the majority of our experiments are performed on the MVTec Anomaly Detection benchmark. MVTec AD contains 15 sub-datasets with a total of 5354 images, 1725 of which are in the test set. Each sub-dataset is divided into nominal-only training data and test sets containing both nominal and anomalous samples for a specific product with various defect types as well as respective anomaly ground truth masks.”
Explanation: This refers to industrial product images used for anomaly detection.
generating EMI patches representations that are related to the EMI; wherein the EMI patches representations of the EMI are selected out of (a) representations of patches of the image of the EMI, or (b) patches of a representation of the image of the EMI;
PNG
media_image2.png
497
350
media_image2.png
Greyscale
Explanation: Roth explicitly extracts patch-level features which directly corresponds to patches of the image and representations (feature embeddings) of patches.
calculating EMI patches representations scores, wherein an EMI patch representation score of a certain EMI patch representation is determined based on similarities between the certain EMI patch representation and other EMI patch representations (3.3. Anomaly Detection with PatchCore (shown above));
Explanation: Roth computes anomaly score based on distances (similarity), where similarity-based scoring is equivalent to distance-based similarity.
and determining a defect related status of the EMI based on at least some of the EMI patches representations scores and on at least one similarity related values.
3.3. Anomaly Detection with PatchCore: “Given s, segmentations follow directly. The image-level anomaly score in Eq. 7 (first line) requires the computation of the anomaly score for each patch through the arg max-operation.”
Explanation: This is used for detection of anomalous (defective) samples, where scores are used to make a decision regarding the anomaly (defect) status.
Regarding Claim 2, Roth teaches the method according to claim 1, wherein the at least one similarity related value is at least one similarity threshold.
4.1 Experimental Details: “Image-level anomaly detection performance is measured via the area under the receiver-operator curve (AUROC) using produced anomaly scores.”
Explanation: Roth discusses thresholded anomaly scoring used for AUROC and detection, where detection requires thresholds.
Regarding Claim 3, Roth teaches the method according to claim 1, wherein the at least one similarity related value is determined based on EMI patches representations scores learnt during a training process (3.3. Anomaly Detection with PatchCore (shown above) and 4.1 Experimental Details (shown above)).
Explanation: Roth uses nominal training data.
Regarding Claim 4, Roth teaches the method according to claim 1, wherein the at least one similarity related value is determined based on statistics of EMI patches representations scores learnt during a training process.
3.3. Anomaly Detection with PatchCore: “To obtain s, we use scaling w on s ∗ to account for the behaviour of neighbour patches…We found this re-weighting to be more robust than just the maximum patch distance.”
Explanation: Roth uses statistical reweighting.
Regarding Claim 5, Roth teaches the method according to claim 1, wherein the at least one similarity related value is determined based on (a) a standard deviation of EMI patches representations scores learnt during a training process, and (b) a mean of EMI patches representations scores learnt during the training process.
3.3. Anomaly Detection with PatchCore: “Additionally, we smoothed the result with a Gaussian of kernel width σ = 4…”
Explanation: Roth discloses distribution-based processing of patch anomaly scores and explicitly applies Gaussian smoothing using σ = 4, which reflects use of statistical dispersion of score distributions. Determining values based on such distributional statistics encompasses determining values based on mean and standard deviation.
Regarding Claim 6, Roth teaches the method according to claim 1, wherein the other EMI patch representations are all EMI patch representations other than the certain EMI patch representation (3.3. Anomaly Detection with PatchCore (shown above)).
Explanation: Roth uses full memory bank M that is used globally for comparisons.
Regarding Claim 7, Roth teaches the method according to claim 1, wherein the other EMI patch representations are only some of all EMI patch representations other than the certain EMI patch representation (Algorithm 1 (shown above)).
3.2. Coreset-reduced patch-feature memory bank: “For notation, we use PatchCore−n% to denote the percentage n to which the 14321 original memory bank has been subsampled to, e.g., PatchCore−1% a 100x times reduction of M.”
Explanation: Roth subsamples patches via coreset.
Regarding Claim 8, Roth teaches the method according to claim 1, wherein the other EMI patch representations are only neighbors of the certain EMI patch representation.
3.3. Anomaly Detection with PatchCore: “If memory bank features closest to anomaly candidate mtest,∗ , m∗ , are themselves far from neighbouring samples and thereby an already rare nominal occurrence, we increase the anomaly score with Nb(m∗ ) the b nearest patch-features in M for test patch-feature m∗.”
Regarding Claim 9, Roth teaches the method according to claim 1, wherein the determining comprises determining that two EMI patches representations are not indicative of a EMI defect when EMI patches representations scores if the two or more EMI patches representations are similar to each other.
3.3. Anomaly Detection with PatchCore: “If memory bank features closest to anomaly candidate mtest,∗ , m∗ , are themselves far from neighbouring samples and thereby an already rare nominal occurrence, we increase the anomaly score with Nb(m∗ ) the b nearest patch-features in M for test patch-feature m∗.”
Explanation: Close neighbors = less anomalous
Regarding Claim 10, Roth teaches the method according to claim 1, wherein the at least some of the EMI patches representations scores are all the EMI patches representations scores.
3.3. Anomaly Detection with PatchCore: “The image-level anomaly score in Eq. 7 (first line) requires the computation of the anomaly score for each patch through the arg max-operation.”
Regarding Claim 11, Roth teaches all of the limitations of claim 1 above because claim 11 recites a non-transitory computer readable medium that performs substantially the same steps as claim 1.
Regarding Claim 12, Roth teaches the non-transitory computer readable medium according to claim 11, and additional limitations are met as in the consideration of claim 2 above.
Regarding Claim 13, Roth teaches the non-transitory computer readable medium according to claim 11, and additional limitations are met as in the consideration of claim 3 above.
Regarding Claim 14, Roth teaches the non-transitory computer readable medium according to claim 11, and additional limitations are met as in the consideration of claim 4 above.
Regarding Claim 15, Roth teaches the non-transitory computer readable medium according to claim 11, and additional limitations are met as in the consideration of claim 5 above.
Regarding Claim 16, Roth teaches the non-transitory computer readable medium according to claim 11, and additional limitations are met as in the consideration of claim 6 above.
Regarding Claim 17, Roth teaches the non-transitory computer readable medium according to claim 11, and additional limitations are met as in the consideration of claim 7 above.
Regarding Claim 18, Roth teaches the non-transitory computer readable medium according to claim 11, and additional limitations are met as in the consideration of claim 8 above.
Regarding Claim 19, Roth teaches the non-transitory computer readable medium according to claim 11, and additional limitations are met as in the consideration of claim 9 above.
Regarding Claim 20, Roth teaches the non-transitory computer readable medium according to claim 11, and additional limitations are met as in the consideration of claim 10 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Weiss (US 11688056 B2) teaches extracting image features, generating vector representations, comparing representations using proximity and similarity, and predicting defect likelihood based on those similarities.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM ADU-JAMFI whose telephone number is (571) 272-9298. The examiner can normally be reached M-T 8:00-6:00.
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, 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.
/WILLIAM ADU-JAMFI/Examiner, Art Unit 2677
/ANDREW W BEE/Supervisory Patent Examiner, Art Unit 2677