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 .
DETAILED ACTION
The response received on 20 July 2026 has been placed in the file and was considered by the examiner. An action on the merit follows.
Response to Amendment
The amendments filed on 2026 July 20 have been fully considered. Response to these amendments is provided below.
Summary of Amendment/ Arguments and Examiner’s Response:
The applicant has amended the claims to include subject matter from a previous claim along with newly claimed subject matter. ON page 14 of the remarks, the applicant repeats the amended limitations and summarizes Gaind. On page 15, the applicant argues Braur fails to cure the deficiency in Gaind regarding because Braur does not discloses “the classifier in the inspection recipe comprises the classifier used to generate the probabilities…”
The examiner disagrees. The combination of references teaches the claimed limitations. Please see how the newly claimed limitations are disclosed by the references in the rejection below.
On page 15 of the remarks, the applicant further states that the rational does not account for the newly claimed requirement of “The classifier comprises…”.
Again, please see the newly claimed limitation addressed in the rejection below.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1, 3, 4, 6, 8-11, 15-23, 25-31, 32-35, 37, 39, 40, 42-48 and are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1, 23 and 32 recite the limitation "the locations of the test sample" in lines 23, 25 and 21, respectively. There is insufficient antecedent basis for this limitation in the claim.
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.
Claims 1, 3, 4, 6, 8, 9, 15-23, 25,-27, 29-35, 37, 39, 40, 42-48 are rejected under 35 U.S.C. 103(a) as being unpatentable over U.S. Patent Application Publication No. 20210109041 (Gaind et al) in view of U.S. Patent Application Publication NO. 20200193588 (Brauer et al).
Regarding claim 32, Gaind et al discloses an inspection method (fig. 3) comprising: developing an inspection recipe (fig. 3, item 304) with steps comprising: generating N inspection images of a preliminary sample with one or more optical inspection sub-systems (fig. 1, item 36) associated with N different optical inspection modes, wherein N is an integer greater than two, i.e. an image from each mode as described in page 4, paragraphs 35 and 37, page 6, paragraph 52-53, wherein each of the N optical inspection modes is associated with unique optical imaging parameters of the one or more optical inspection sub-systems, i.e. the different wavelength or light channel (page 4, paragraph 35, pages 5-6 paragraph 51), wherein locations in the N inspection images of the preliminary sample correspond to locations on the preliminary sample, since the images are taken from the locations at the preliminary sample (page 6, paragraph 53); generating probabilities that each of the locations of the preliminary sample are in background (nuisance, page 8, paragraph 66) or defect classes using a classifier with the inspection images from at least some combinations of a number M of the optical inspection modes (page 8, paragraph 66), wherein M is an integer greater than one and less than N and corresponds to a number of the optical inspection modes to include in the inspection recipe, i.e. a combination of the modes that does not include all the modes and thus less than N (page 6, paragraph 56); and selecting one of the combinations of M of the optical inspection modes as a selected combination based on a metric, a quantitative measure (fig. 3, item 304) describing a distinction between the background and defect classes (fig. 3, item 304, page 8, paragraph 66, page 6, paragraph 56); and identifying defects on a test sample using M inspection images of the test sample generated based on the inspection recipe with the selected combination of M of the optical inspection modes, since the selected modes are used in inspection on other specimens (page 2, paragraph 12). Gaind et al further discloses the specified amount of images for inspection is M images of modes determined of the inspection recipe (page 6, paragraph 56), that classes that are classified are background and defect classes (page 3, paragraph 300), that the classifier is used in the inspections classification because the classifier is used to find the recipe (fig. 3), wherein the classifier used for training the optical inspection modes generates the probabilities for the selected combination of M of the optical inspection modes (page 6, paragraph 56).
Gaind et al does not disclose expressly identifying defects of the specimen using the specified amount of inspection images from the recipe of the test sample generated based on the inspection recipe with the selected combination of the amount of the recipe of the optical inspection modes comprises: classifying the locations of the test sample into the classes based on the specified amount of the recipe inspection images, and that the classifier in the inspection recipe is the same as the classifier used in training.
Brauer et al discloses identifying defects of the specimen using the specified amount of inspection images from the recipe of the test sample generated based on the inspection recipe with the selected combination of the amount of the recipe of the optical inspection modes (fig. 2, item 226) comprises: classifying the locations of the test sample into the classes based on the specified amount of the recipe inspection images and the classifier in the inspection recipe, since the recipe is used in inspection that specifies the amount of images and scans and processes them (fig. 2, item 226), and the classifier is used to identify defects (fig. 2, item 226) and that the classifier in the inspection recipe is the same as the classifier used in training the optical inspection modes by disclosing the optical modes correspond to the scanning of the wafer including identifying defects accordingly (page 3, paragraph 31), thus disclosing the choice of optical modes corresponds to the classification/ identification of defects, which occurs as disclosed in fig. 2, item 226.
Gaind et al & Brauer et al are combinable because they are from the same field of endeavor, i.e. image recipe used in inspection.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to follow the recipe during inspection and use the same classifier in training as in inspection.
The suggestion/motivation for doing so would have been to provide a more robust system by using the recipe as intended and maintaining consistency.
Therefore, it would have been obvious to combine the system of Gaind et al with following the recipe of Brauer et al to obtain the invention as specified in claim 32.
Claim 1 is rejected for the same reasons as claim 32. Thus, the arguments analogous to that presented above for claim 32 are equally applicable to claim 1. Claim 1 distinguishes from claim 32 only in that claim 1 is an inspection system comprising a controller including one or more processors to execute program instructions causing the one or more processors to execute the method of claim 32. Gaind et al teaches further this feature, i.e. system with controller (fig. 2, item 204) to execute instructions (fig. 2, item 202).
Claim 23 is rejected for the same reasons as claim 1. Thus, the arguments analogous to that presented above for claim 1 are equally applicable to claim 23. Claim 23 distinguishes from claim a only in that claim 23 claims that the system comprises one or more optical inspection subsystems, and the controller is coupled to the one or more optical sub -systems.. Gaind et al teaches further this feature, i.e. fig. 1, items 36, 102.
Regarding claim 3, Gaind et al discloses developing the inspection recipe further includes registering the N inspection images of the preliminary sample (page 6, paragraph 53).
Regarding claim 4, Gaind et al discloses N inspection images (fig. 3, item 300). Brauer et al also discloses inspection images of the preliminary sample have a common number of pixels, since the common number of pixels are compared as disclosed in page 2, paragraph 23.
Regarding claim 6, Gaind et al discloses N inspection images (fig. 3, item 300), and M inspection images will be for the test sample in the recipe (fig. 3, item 304).
Brauer et al discloses inspection images of the preliminary sample and the inspection images of the test sample correspond to difference images based on differences between raw images and reference images from the one or more optical inspection sub-systems, the difference image data for the inspection images (page 2, paragraphs 15, 23, pages 2-3, paragraph 25).
Regarding claim 8, Gaind et al discloses the defect classes include a two or more defect classes, i.e. multiple defect types (page 2, paragraph 20).
Regarding claim 9, Gaind et al discloses the classifier comprises: an unsupervised classifier (page 7, paragraph 58).
Regarding claim 15, Brauer et al discloses the classifier comprises: a neural network (page 3, paragraph 36).
Regarding claim 16, Gaind et al discloses N inspection images (fig. 3, item 300), and M inspection images will be for the test sample in the recipe (fig. 3, item 304), wherein generating probabilities that each of the locations of the preliminary sample are in background or defect classes using the classifier with the inspection images from at least some combinations of the number M of the optical inspection modes comprises: generating probabilities that each of the locations of the preliminary sample are in background or defect classes using a classifier with the inspection images from at least some combinations of the number M of the optical inspection modes (page 8, paragraph 66), as explained above. Brauer et al discloses the classifier includes a neural network (page 3, paragraph 36)
Regarding claim 17, Gaind et al discloses generating probabilities that each of the locations of the preliminary sample are in background or defect classes using the classifier with the inspection images from at least some combinations of the number M of the optical inspection modes comprises: generating probabilities that each of the locations of the preliminary sample are in background or defect classes using the classifier with the inspection images from all of the combinations of the number M of the optical inspection modes, i.e. all of the available mode combinations (page 6, paragraph 56).
Regarding claim 18, Gaind et al discloses developing the inspection recipe further comprises: selecting one of the optical inspection modes as a primary mode, i.e. one of the modes of the combination of fig. 3, item 304, wherein generating probabilities that each of the locations of the preliminary sample are in background or defect classes using the classifier with the inspection images from at least some combinations of the number M of the optical inspection modes comprises: generating probabilities that each of the locations of the preliminary sample are in background or defect classes using the classifier with the inspection images from at least some of the combinations of the number M of the optical inspection modes that include the primary mode (fig. 3, item 302, pages 7-8, paragraph 66).
Regarding claim 19, Gaind et al discloses the N different optical inspection modes are associated with difference in at least one of an illumination wavelength (page 6, paragraph 51), an illumination polarization, or an illumination angle.
Regarding claim 20, Gaind et al discloses the N different optical inspection modes are associated with difference in at least one of a wavelength (page 6, paragraph 51), a polarization, or an angle of light collected by the one or more optical inspection sub-systems and directed to a detector (fig. 1).
Regarding claim 21, Gaind et al discloses M equals two (page 6, paragraph 56).
Regarding claim 22, Gaind et al discloses N is greater than or equal to three (page 4, paragraph 35).
Regarding claim 25, Gaind et al discloses the one or more optical inspection sub- systems comprise: a single optical inspection sub-system (fig. 1, item 36).
Claims 26, 27, 29, 30 and 31 are rejected for the same reasons as claims 6, 9, 15, 19 and 20, respectively. Thus, the arguments analogous to that presented above for claims 6, 9, 15, 19 and 20 are equally applicable to claims 26, 27, 29, 30 and 31. Claims 26, 27, 29, 30 and 31 distinguishes from claim 6, 9, 15, 19 and 20 only in that they have different dependencies, both of which have been previously rejected. Therefore, prior art applies.
Claims 34, 35, 37, 39, 40, 42, 43, 44, 45, 46, 47 and 48 are rejected for the same reasons as claims 3, 4, 6, 8, 9, 15, 17, 18, 19, 20, 21 and 22, respectively. Thus, the arguments analogous to that presented above for claims 3, 4, 6, 8, 9, 15, 17, 18, 19, 20, 21 and 22 are equally applicable to claims 34, 35, 37, 39, 40, 42, 43, 44, 45, 46, 47 and 48 . Claims 34, 35, 37, 39, 40, 42, 43, 44, 45, 46, 47 and 48 distinguishes from claim 3, 4, 6, 8, 9, 15, 17, 18, 19, 20, 21 and 22 only in that they have different dependencies, both of which have been previously rejected and claim 44 states “some combinations” instead of “some of the combinations”, which can be interpreted as the same combinations. Therefore, prior art applies.
Claim 10 is rejected under 35 U.S.C. 103(a) as being unpatentable over Gaind et al in view of Brauer et al, as applied to claim 9 above, and further in view of U.S. Patent Application Publication No. 20210201460 (Gong et al).
Regarding claim 10, Gaind et al (as modified by Brauer et al) discloses all of the claimed elements as set forth above and incorporated herein by reference.
Gaind et al (as modified by Brauer et al) does not disclose expressly the unsupervised classifier implements a soft clustering technique.
Gong et al discloses classifiers for defects include a soft clustering technique (page 3, paragraph 29).
Gaind et al (as modified by Brauer et al) & Gong et al are combinable because they are from the same field of endeavor, i.e. defect inspection.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to classify using soft clustering technique.
The suggestion/motivation for doing so would have been to provide a more robust system by allowing a known technique for unsupervised learning.
Therefore, it would have been obvious to combine the system of Gaind et al (as modified by Brauer et al) with the soft clustering of Gong et al to obtain the invention as specified in claim 10.
Claim 11 is rejected under 35 U.S.C. 103(a) as being unpatentable over Gaind et al in view of Brauer et al and Gong et al, as applied to claim 10 above, and further in view of U.S. Patent Application Publication NO. 20110314049 (Poirier et al).
Regarding claim 11, Gaind et al (as modified by Brauer et al and Gong et al) discloses all of the claimed elements as set forth above and incorporated herein by reference.
Gaind et al (as modified by Brauer et al and Gong et al) does not disclose expressly the soft clustering technique comprises: a Gaussian mixtures model (GMM) technique.
Poirier et al discloses the soft clustering technique comprises: a Gaussian mixtures model (GMM) technique (page 4, paragraph 40).
Gaind et al (as modified by Brauer et al and Gong et al) and Poirier et al are combinable because they are from the same field of endeavor, i.e. soft clustering.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to use a GMM.
The suggestion/motivation for doing so would have been to provide a more robust system by using successful clustering techniques for visual data.
Therefore, it would have been obvious to combine the system of Gaind et al(as modified by Brauer et al and Gong et al) with the GMM technique of Poirier et al to obtain the invention as specified in claim 11.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection 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 nonprovisional extension fee (37 CFR 1.17(a)) 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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Kathleen Yuan Dulaney whose telephone number is (571)272-2902. The examiner can normally be reached M-F: 9AM-5PM.
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, Emily Terrell can be reached at 5712703717. 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.
/KATHLEEN Y DULANEY/Primary Examiner, Art Unit 2666 8/19/2026
Prosecution Insights