Notice of Pre-AIA or 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 .
DETAILED ACTION
2. The United States Patent & Trademark Office appreciates the application that is by the inventor/assignee. The United States Patent & Trademark Office reviewed the following application and has made the following comments below.
Information Disclosure Statement
3. The information disclosure statement (IDS) submitted on 4/11/2024. The submission is in
compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure
statement is being considered by the examiner.
Claim Rejections - 35 USC § 103
4. 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.
5. Claims 1-6 and 8-18 are rejected under 35 U.S.C 103 as being unpatentable over Staroselsky et al. (US Patent Pub. No. US 7549339 B2, hereafter referred to as Staroselsky) in view of Cha et al. (US Patent Pub. No. US 20240005645 A1, hereafter referred to as Cha) in further view of Kitchen et al. (US Patent Pub. No. 20210318673 A1, hereafter referred to as Kitchen).
6. Regarding Claim 1, Staroselsky teaches a method comprising: generating a training thermal acoustic imaging (TAI) scan of a first component (Fig. 2 and col 2 lines 32-45, Staroselsky teaches a procedure for part inspection using heat and vibrations, where intensity is identified with thermal images.) and wherein the training TAI scan includes a plurality of frames showing known positive and false samples of a defect within the training TAI scan of the first component (Fig. 2 and col 2 lines 32-45, Staroselsky teaches several images being taken to capture results of temperature over testing time to be compared with baselines for determining the presence and absence of defects. The Examiner interprets the capturing of results of temperature of testing time as obtaining samples and the comparison of obtained results with baselines as showing known positive and false samples of a defect.).
PNG
media_image1.png
696
1086
media_image1.png
Greyscale
Staroselsky does not teach applying a visual feature extractor model to the plurality of frames within the training TAI scan, extracting a plurality of spatial features for a signal corresponding to a selected indication type shown in the training TAI scan using the visual feature extractor model, concatenating the plurality of spatial features of the signal from each frame of the plurality of frames to generate a time series value for the respective frame, combining a plurality of the time series values into multiple sequence data for the training TAI scan, wherein the multiple sequence data includes a plurality of temporal features, and training a neural network model using the multiple sequence data to predict the selected indication type in the training TAI scan as being a defect or a non-defect within the first component.
Cha is in the same field of defect detection using imaging data. Further Cha teaches applying a visual feature extractor model to the plurality of frames within the training TAI scan (paragraphs 2, 15, 21, 87, and 145, Cha teaches features relevant to the article of interest, such as a defect in a surface for example a crack, being extracted from thermographic images, which are images obtained using an IR camera. All of this is done for specific analysis of visual aspects to measure the quality of the images.), extracting a plurality of spatial features for a signal corresponding to a selected indication type shown in the training TAI scan using the visual feature extractor model (paragraph 15, 21, 135-136, 160, and 167, Cha teaches extraction of features that provide information on shape, location, arrangement, and structural relationships within an image relating to potential defects such as cracks or other defects in a surface, where the features extracted provide information on length, width, thickness, depth, space, and other various geometrical factors of the damage.), and concatenating the plurality of spatial features of the signal from each frame of the plurality of frames to generate a time series value for the respective frame (paragraph 18 and 25-28, Cha teaches multiple time series generated to concatenate outputs of the submodules used to obtain feature data of the thermographic images.).
Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention to modify the invention of Staroselsky by adding
the extraction method of visual aspects representative of defects from thermographic images that is taught by Cha to make an invention thar enhances detection precision and accelerate inspections; thus one of ordinary skill in the art would be motivated to combine the references since there is a need for a fast, robust, and automated IRT image analysis method to detect and localize the internal damage of concrete specimens (paragraphs 5, Cha).
Staroselsky in view of Cha does not teach combining a plurality of the time series values into multiple sequence data for the training TAI scan, wherein the multiple sequence data includes a plurality of temporal features and training a neural network model using the multiple sequence data to predict the selected indication type in the training TAI scan as being a defect or a non-defect within the first component.
[AltContent: arrow][AltContent: arrow] Kitchen is in the same field of defect detection using imaging data. Further, Kitchen teaches combining a plurality of the time series values into multiple sequence data for the training TAI scan, wherein the multiple sequence data includes a plurality of temporal features (paragraph 7, 39, 66, 70, and 101, Kitchen teaches the capture and eventual use of sequential imagery data relating to the in situ wielding process that is used to gain information on thermal characteristics using convolutional neural network training algorithms in conjunction with time series data points, where multiple sequence images are converted into data arrays and the images are used to capture temporal features such as temporal patterns of weld shape, speed spatter, and thermal pattern.) and training a neural network model using the multiple sequence data to predict the selected indication type in the training TAI scan as being a defect or a non-defect within the first component (Fig. 1 and 6A, paragraphs 38-39, 62-63, 71, and 105, Kitchen teaches training a neural network model using multiple sequence data points to predict and identify the presence or absence of weld qualities, defects, and other characteristics relating weld machinery.).
PNG
media_image2.png
812
550
media_image2.png
Greyscale
PNG
media_image3.png
584
888
media_image3.png
Greyscale
Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention to modify the invention of Staroselsky by incorporating a method using neural networks with sequential imagery data in conjunction with time series data points to identify weld qualities and defects that is taught by Kitchen to make an invention that enhances detection precision and accelerate inspections; thus one of ordinary skill in the art would be motivated to combine the references since routine repairs are performed to ensure quality (e.g., replacing or welding defective parts), sometimes without the knowledge of what caused the defects, while conventional techniques for welding quality control are error-prone and cost intensive (paragraph 3, Kitchen).
Thus, the claimed subject matter would have been obvious to a person having ordinary
skill in the art before the effective filing date.
7. In regards to Claim 2, Staroselsky in view of Cha in further view of Kitchen teaches wherein the visual feature extractor model is a trained visual feature extractor model (paragraphs 15, 87. 145, and 187, Cha teaches a first convolutional neural network module AGAN being configured for the extraction of features for the generation of a feature map using key features of thermographic images.).
8. In regards to Claim 3, Staroselsky in view of Cha in further view of Kitchen teaches wherein generating a training TAI scan includes capturing thermal radiation using an inspection system (col 2 lines 9-15, 32-39, 45-51, Staroselsky teaches thermal energy dissipation recorded of thermal acoustic images, which includes thermal radiation as well as several images being taken to capture transient, changing temperature or the course of tests to be compared with baselines, where the images are captured using infrared cameras and the images are digitized to obtain thermal information. Measured temperatures, obtained using an infrared camera system are used to inversely solve for transient heat transfer.).
9. In regards to Claim 4, Staroselsky in view of Cha in further view of Kitchen teaches a further comprising generating a plurality of video images corresponding to the plurality of frames (Fig. 2 and col 2 lines 32-45, Staroselsky teaches several images being taken to capture results of temperature over testing time to be compared with baselines for determining the presence and absence of defects.).
10. In regards to Claim 5, Staroselsky in view of Cha in further view of Kitchen teaches wherein the plurality of video images capture the plurality of spatial features (paragraph 15, 21, 135-136, 160, and 167, Cha teaches extraction of features that provide information on shape, location, arrangement, and structural relationships within an image relating to potential defects such as cracks or other defects in a surface, where the features extracted provide information on length, width, thickness, depth, space, and other various geometrical factors of the damage.).
11. In regards to Claim 6, Staroselsky in view of Cha in further view of Kitchen teaches wherein one of the plurality of spatial features relates to temperature data captured within each frame of the plurality of frames of the training TAI scan (Fig. 1 and 10, paragraph 135 Cha teaches geometrical shapes and characteristics such as width, length, and thickness of internal damage segmentation after obtaining the IR image data using a thermal camera.).
PNG
media_image4.png
498
1066
media_image4.png
Greyscale
PNG
media_image5.png
744
768
media_image5.png
Greyscale
[AltContent: arrow][AltContent: arrow]12. In regards to Claim 8, Staroselsky in view of Cha in further view of Kitchen teaches a (Fig. 14B and paragraph 151, Cha teaches GAN models, which extract key features such as spatial features from thermographic images for the generation of a feature map, generate only specific limited patterns again and again.).
PNG
media_image6.png
286
696
media_image6.png
Greyscale
13. In regards to Claim 9, Staroselsky in view of Cha in further view of Kitchen teaches wherein the pattern corresponds to the known defect (paragraphs 79, 151, 181-193, Cha teaches the generation of only specific limited patterns to detect an article of interest such as a defect in a surface, for example a crack. The Examiner interprets this as a corresponding to the known defect.).
14. Regarding Claim 10, Staroselsky teaches a method comprising: receiving an initial thermal acoustic imaging scan receiving an initial thermal acoustic imaging (TAI) scan of a component (Fig. 2 and col 2 lines 32-45, Staroselsky teaches a procedure for part inspection using heat and vibrations, where intensity is identified with thermal images.), wherein the initial TAI scan includes a plurality of frames showing an identified possible defect within the component (Fig. 2 and col 2 lines 32-45, Staroselsky teaches a procedure for part inspection using heat and vibrations, where intensity is identified with thermal images.), generating a training TAI scan (Fig. 2 and col 2 lines 32-45, Staroselsky teaches several images being taken to capture results of temperature over testing time to be compared with baselines for determining the presence and absence of defects.), and wherein the training TAI scan includes a plurality of frames showing known positive and false samples of a defect within a training component (Fig. 2 and col 2 lines 32-45, Staroselsky teaches several images being taken to capture results of temperature over testing time to be compared with baselines for determining the presence and absence of defects. The Examiner interprets the capturing of results of temperature of testing time as obtaining samples and the comparison of obtained results with baselines as showing known positive and false samples of a defect.).
Staroselsky does not teach applying a trained neural network model to the plurality of frames of the initial TAI scan, predicting whether the identified possible defect is an actual defect using the trained neural network model, applying a visual feature extractor model to the plurality of frames within the training TAI scan, extracting a plurality of spatial features for a signal corresponding to a selected indication type shown in the training TAI scan using the visual feature extractor model, concatenating the plurality of spatial features of the signal from each frame of the plurality of frames to generate a time series value for the respective frame, combining a plurality of the time series values into multiple sequence data for the training TAI scan, and wherein the multiple sequence data includes a plurality of temporal features; and training the trained neural network model using the multiple sequence data to predict the selected indication type as being a defect or non-defect within the training TAI scan.
Cha is in the same field of defect detection using imaging data. Further Cha teaches applying a visual feature extractor model to the plurality of frames within the training TAI scan (paragraphs 2, 15, 21, 87, and 145, Cha teaches features relevant to the article of interest, such as a defect in a surface for example a crack, being extracted from thermographic images, which are images obtained using an IR camera. All of this is done for specific analysis of visual aspects to measure the quality of the images.), extracting a plurality of spatial features for a signal corresponding to a selected indication type shown in the training TAI scan using the visual feature extractor model (paragraph 15, 21, 135-136, 160, and 167, Cha teaches extraction of features that provide information on shape, location, arrangement, and structural relationships within an image relating to potential defects such as cracks or other defects in a surface, where the features extracted provide information on length, width, thickness, depth, space, and other various geometrical factors of the damage.), and concatenating the plurality of spatial features of the signal from each frame of the plurality of frames to generate a time series value for the respective frame (paragraph 18 and 25-28, Cha teaches multiple time series generated to concatenate outputs of the submodules used to obtain feature data of the thermographic images.).
Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention to modify the invention of Staroselsky by adding
the extraction method of visual aspects representative of defects from thermographic images that is taught by Cha to make an invention thar enhances detection precision and accelerate inspections; thus one of ordinary skill in the art would be motivated to combine the references since there is a need for a fast, robust, and automated IRT image analysis method to detect and localize the internal damage of concrete specimens (paragraphs 5, Cha).
Staroselsky in view of Cha does not teach applying a trained neural network model to the plurality of frames of the initial TAI scan, predicting whether the identified possible defect is an actual defect using the trained neural network model, combining a plurality of the time series values into multiple sequence data for the training TAI scan, and wherein the multiple sequence data includes a plurality of temporal features; and training the trained neural network model using the multiple sequence data to predict the selected indication type as being a defect or non-defect within the training TAI scan.
Kitchen is in the same field of defect detection using imaging data. Further Kitchen teaches applying a trained neural network model to the plurality of frames of the initial TAI scan (Fig. 1 and 6A, paragraphs 38-39, 62-63, 71, and 105, Kitchen teaches training a neural network model using multiple sequence data points to predict and identify the presence or absence of weld qualities, defects, and other characteristics relating weld machinery.), predicting whether the identified possible defect is an actual defect using the trained neural network model (Fig. 1 and 6A, paragraphs 38-39, 62-63, 71, and 105, Kitchen teaches training a neural network model using multiple sequence data points to predict and identify the presence or absence of weld qualities, defects, and other characteristics relating weld machinery.), combining a plurality of the time series values into multiple sequence data for the training TAI scan (paragraph 7, 39, 66, 70, and 101, Kitchen teaches the capture and eventual use of sequential imagery data relating to the in situ wielding process that is used to gain information on thermal characteristics using convolutional neural network training algorithms in conjunction with time series data points, where multiple sequence images are converted into data arrays and the images are used to capture temporal features such as temporal patterns of weld shaped, speed spatter, and thermal pattern.), wherein the multiple sequence data includes a plurality of temporal features; and training the trained neural network model using the multiple sequence data to predict the selected indication type as being a defect or non-defect within the training TAI scan (Fig. 1 and 6A, paragraphs 38-39, 62-63, 71, and 105, Kitchen teaches training a neural network model using multiple sequence data points to predict and identify the presence or absence of weld qualities, defects, and other characteristics relating weld machinery.).
Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention to modify the invention of Staroselsky by incorporating a method using neural networks with sequential imagery data in conjunction with time series data points to identify weld qualities and defects that is taught by Kitchen to make an invention that enhances detection precision and accelerate inspections; thus one of ordinary skill in the art would be motivated to combine the references since routine repairs are performed to ensure quality (e.g., replacing or welding defective parts), sometimes without the knowledge of what caused the defects, while conventional techniques for welding quality control are error-prone and cost intensive (paragraph 3, Kitchen).
Thus, the claimed subject matter would have been obvious to a person having ordinary
skill in the art before the effective filing date.
15. In regards to Claim 11, Staroselsky in view of Cha in further view of Kitchen teaches a further comprising capturing the training TAI scan using an infrared camera (col 2 lines 9-15, 32-39, 45-51, Staroselsky teaches thermal energy dissipation recorded of thermal acoustic images, which includes thermal radiation as well as several images being taken to capture transient, changing temperature or the course of tests to be compared with baselines, where the images are captured using infrared cameras and the images are digitized to obtained thermal information. Measured temperatures, obtained using an infrared camera system are used to inversely solve for transient heat transfer.).
16. In regards to Claim 12, Staroselsky in view of Cha in further view of Kitchen teaches wherein the plurality of spatial features includes at least one feature related to heat captured by the infrared camera (col 2 lines 9-15, Staroselsky teaches the parameterization of the energy dissipation or release rate of heat, where it is mentioned that the temperature rise depends upon crack geometry, location, and energy dissipation.).
17. In regards to Claim 13, Staroselsky in view of Cha in further view of Kitchen teaches wherein the visual feature extractor model is a trained visual feature extractor model (paragraphs 15, 87. 145, and 187, Cha teaches a first convolutional neural network module AGAN being configured to extract features for the generation of a feature map using key features of thermographic images.).
18. In regards to Claim 14, Staroselsky in view of Cha in further view of Kitchen teaches a further comprising identifying a pattern within the plurality of frames using the concatenated plurality of spatial and temporal features (Fig. 14B and paragraph 151, Cha teaches GAN models, which extract key features such as spatial features from thermographic images for the generation of a feature map, generate only specific limited patterns again and again.).
19. In regards to Claim 15, Staroselsky in view of Cha in further view of Kitchen teaches wherein the pattern corresponds to the known defect (paragraphs 79, 151, 181-193, Cha teaches the generation of only specific limited patterns to detect an article of interest such as a defect in a surface, for example a crack. The Examiner interprets this as a corresponding to the known defect.).
20. Regarding Claim 16, Staroselsky teaches a method comprising: generating a training thermal acoustic imaging (TAI) scan of a first component (Fig. 2 and col 2 lines 32-45, Staroselsky teaches a procedure for part inspection using heat and vibrations, where intensity is identified with thermal images.) and wherein the training TAI scan includes a plurality of frames showing at least one indication within the training TAI scan of the first component (Fig. 2 and col 2 lines 32-45, Staroselsky teaches several images being taken to capture results of temperature over testing time to be compared with baselines for determining the presence and absence of defects. The Examiner interprets the capturing of results of temperature of testing time as obtaining samples and the comparison of obtained results with baselines as showing known positive and false samples of a defect.).
Staroselsky does not teach generating video data for the at least one indication within the plurality of frames, wherein the video data uses three different channels, wherein at least one channel includes temperature data of the at least one indication, applying a visual feature extractor model to the video data for the plurality of frames within the training TAI scan, extracting a plurality of spatial features for the video data corresponding to a selected indication type shown in the training TAI scan using the visual feature extractor model, concatenating the plurality of spatial features of the signal from each frame of the plurality of frames to generate a time series value for the respective frame, combining a plurality of the time series values into multiple sequence data for the training TAI scan, wherein the multiple sequence data includes a plurality of temporal features, and training a neural network model using the multiple sequence data to predict the selected indication type in the training TAI scan as being a defect or a non-defect within the first component.
Cha is in the same field of defect detection using imaging data. Further Cha teaches applying a visual feature extractor model to the video data for the plurality of frames within the training TAI scan (paragraphs 2, 15, 21, 87, and 145, Cha teaches features relevant to the article of interest, such as a defect in a surface for example a crack, being extracted from thermographic images, which are images obtained using an IR camera. All of this is done for specific analysis of visual aspects to measure the quality of the images.), extracting a plurality of spatial features for the video data corresponding to a selected indication type shown in the training TAI scan using the visual feature extractor model (paragraph 15, 21, 135-136, 160, and 167, Cha teaches extraction of features that provide information on shape, location, arrangement, and structural relationships within an image relating to potential defects such as cracks or other defects in a surface, where the features extracted provide information on length, width, thickness, depth, space, and other various geometrical factors of the damage.), and concatenating the plurality of spatial features of the signal from each frame of the plurality of frames to generate a time series value for the respective frame (paragraph 18 and 25-28, Cha teaches multiple time series generated to concatenate outputs of the submodules used to obtain feature data of the thermographic images.).
Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention to modify the invention of Staroselsky by adding
the extraction method of visual aspects representative of defects from thermographic images that is taught by Cha to make an invention thar enhances detection precision and accelerate inspections; thus one of ordinary skill in the art would be motivated to combine the references since there is a need for a fast, robust, and automated IRT image analysis method to detect and localize the internal damage of concrete specimens (paragraphs 5, Cha).
Staroselsky in view of Cha does not teach generating video data for the at least one indication within the plurality of frames, wherein the video data uses three different channels, wherein at least one channel includes temperature data of the at least one indication, combining a plurality of the time series values into multiple sequence data for the training TAI scan, wherein the multiple sequence data includes a plurality of temporal features, and training a neural network model using the multiple sequence data to predict the selected indication type in the training TAI scan as being a defect or a non-defect within the first component.
Kitchen is in the same field of defect detection using imaging data. Further Kitchen teaches generating video data for the at least one indication within the plurality of frames (paragraphs 38 and 66, Kitchen teaches the extraction of sequenced imagery data from still or video frames during the process of understanding thermal characteristics of welded machinery, which would include an engine fan blade.), wherein the video data uses three different channels, wherein at least one channel includes temperature data of the at least one indication (paragraphs 38 and 66, Kitchen teaches the extraction of sequenced imagery data from still or video frames during the process of understanding thermal characteristics of welded machinery, which would include an engine fan blade.), combining a plurality of the time series values into multiple sequence data for the training TAI scan, wherein the multiple sequence data includes a plurality of temporal features (paragraph 7, 39, 66, 70, and 101, Kitchen teaches the capture and eventual use of sequential imagery data relating to the in situ wielding process that is used to gain information on thermal characteristics using convolutional neural network training algorithms in conjunction with time series data points, where multiple sequence images are converted into data arrays and the images are used to capture temporal features such as temporal patterns of weld shaped, speed spatter, and thermal pattern.); and training a neural network model using the multiple sequence data to predict the selected indication type in the training TAI scan as being a defect or a non-defect within the first component (Fig. 1 and 6A, paragraphs 38-39, 62-63, 71, and 105, Kitchen teaches training a neural network model using multiple sequence data points to predict and identify the presence or absence of weld qualities, defects, and other characteristics relating weld machinery.).
Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention to modify the invention of Staroselsky by incorporating a method using neural networks with sequential imagery data in conjunction with time series data points to identify weld qualities and defects that is taught by Kitchen to make an invention that enhances detection precision and accelerate inspections; thus one of ordinary skill in the art would be motivated to combine the references since routine repairs are performed to ensure quality (e.g., replacing or welding defective parts), sometimes without the knowledge of what caused the defects, while conventional techniques for welding quality control are error-prone and cost intensive (paragraph 3, Kitchen).
Thus, the claimed subject matter would have been obvious to a person having ordinary
skill in the art before the effective filing date.
21. In regards to Claim 17, Staroselsky in view of Cha in further view of Kitchen teaches a further comprising including an indication annotation with the multiple sequence data to the neural network model (Fig. 15 and paragraphs 154 and 185, Cha teaches indications in case 1 and case 2 data, where red dashed circles are the indication in case 1 for noise in the thermal image obtained.).
PNG
media_image7.png
704
775
media_image7.png
Greyscale
22. In regards to Claim 18, Staroselsky in view of Cha in further view of Kitchen teaches a further comprising identifying the at least one indication within the plurality of frames of the training TAI scan (Fig. 15 and paragraphs 154 and 185, Cha teaches indications in case 1 and case 2 data, where red dashed circles are the indication in case 1 for noise in the thermal image obtained.).
23. Claims 19-20 are rejected under 35 U.S.C 103 as being unpatentable over Staroselsky et al. (US Patent Pub. No. US 7549339 B2, hereafter referred to as Staroselsky) in view of Cha et al. (US Patent Pub. No. US 20240005645 A1, hereafter referred to as Cha) in further view of Kitchen et al. (US Patent Pub. No. 20210318673 A1, hereafter referred to as Kitchen) furthermore in view of Sofer et al. (US Patent Pub. No. US20180306728 A1, hereafter referred to as Sofer).
24. Regarding Claim 19, Staroselsky in view of Cha in further view of Kitchen teaches the method of Claim 18 for training TAI data identifying at least one indication within the plurality of frame of the training TAI scan.
Staroselsky in view of Cha in further view of Kitchen does not teach wherein the at least one indication includes a first indication and a second indication.
Sofer is in the same field of defect detection using imaging data. Further Sofer teaches wherein the at least one indication includes a first indication and a second indication (paragraph 14-15, Sofer teaches a convergence of a number of indications that a potential defect is valid.).
Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention to modify the invention of Staroselsky by adding the merging together of indications that would identify a potential defect that is taught by Sofer to make an invention that would quicken precise defect detection and accelerate inspections; thus one of ordinary skill in the art would be motivated to combine the references since there is a need of manufacturing processes and examinations with error indications, faults, and false positive findings to generate one or more ways for examination and/or parts thereof; inspection, e.g., scanning in a single or in multiple scans; reviewing; measuring and/or other operations provided with regard to the microelectromechanical devices such as wafers or parts thereof using the same or different inspection tools (paragraphs 14-15, Sofer).
Thus, the claimed subject matter would have been obvious to a person having ordinary
skill in the art before the effective filing date.
25. In regards to Claim 20, Staroselsky in view of Cha in further view of Kitchen furthermore in view of Sofer teaches wherein the first indication is a positive sample of a defect and the second indication is a false sample of a defect (Fig. 3 and paragraphs 104-105, Sofer teaches a review of a potential defect to determine if it is a true defect or not, using the convergence of a number of indications, where a confidence level is used to determine whether a potential defect is true or false. The Examiner interprets a confidence level representing a true defect as a first indication of a positive sample of a defect and a confidence level representing a false defect as a second indication of false sample of defect.).
PNG
media_image8.png
856
624
media_image8.png
Greyscale
Allowable Subject Matter
26. Claim 7 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claim.
Regarding Claim 7, no prior art teaches a trained neural network applied to a subsequent TAI scan to predict whether the subsequent scan includes a possible defect or non-defect for a second component.
Conclusion
27. Any inquiry concerning this communication or earlier communications from the
examiner should be directed to LOUIS NWUHA whose telephone number is (571)272 -0219.
The examiner can normally be reached Monday to Friday 8 am to 5 pm.
28. 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.
29. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s
supervisor, Oneal Mistry can be reached at 3134464912. The fax phone number for the
organization where this application or proceeding is assigned is 571-273-8300.
30. 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.
/LOUIS NWUHA/Examiner, Art Unit 2674
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674