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 .
The action is responsive to the following communication: an application filed on 01/08/2024 where:
Claims 1-20 are currently pending.
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sakai et al. (US 2007/0133863, hereinafter Sakai) in view of Marturi Naresh et al. ("Fast image drift compensation in scanning electron microscope using image registration", 2013 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), IEEE, 17 August 2013 (2013-08-17), pages 807-812, XP032523033, ISSN: 2161-8070, DOI: 10.1109/COASE.2013.6653936 [retrieved on 2013-11-03], hereinafter Marturi).
Regarding claim 1, Sakai teaches: A method for correcting distortion of an inspection image (Abstract alignment method, [0008], The present invention provides a high-precision alignment method, device and code for inspections that compare an inspection image with a reference image and detect defects from their differences.), comprising:
acquiring an inspection image (see, fig. 3, inspection image, [0040], FIG. 5 shows an embodiment of a bright field inspection device of the present invention. Item 11 denotes a specimen to be inspected such as a semiconductor wafer);
determining local alignment results for a plurality of patches of the inspection image based on a reference image corresponding to the inspection image (Abstract, In one embodiment an inspection image and a reference image are divided into multiple regions. An offset is calculated for each pair of sub-images. Out of these multiple offsets, only the offsets with high reliability are used to determine an offset for the entire image. This allows high-precision alignment with little or no dependency on pattern density or shape, differences in luminance between images, and uneven luminance within individual images.).
Sakai does not explicitly teach: for each subset of a plurality of subsets of the local alignment results:
determining an alignment model based on the subset of the local alignment results, and
evaluating the alignment model based on a fit of the alignment model to a remainder set of the local alignment results;
selecting one alignment model among the plurality of alignment models based on the evaluations; and
correcting a distortion of the inspection image based on the selected alignment model.
However, Marturi teaches: for each subset of a plurality of subsets of the local alignment results:
determining an alignment model based on the subset of the local alignment results, and
evaluating the alignment model based on a fit of the alignment model to a remainder set of the local alignment results; selecting one alignment model among the plurality of alignment models based on the evaluations (p. 809, col. 2, second paragraph discloses that RANSAC is used to find the best alignment model (D1, p. 809, col. 2: "find other keypoint correspondances such that their distances from the current model are small), i.e. the best homography (D1, p. 809, col. 2: "choose the homography with largest consensus set.); and
correcting a distortion of the inspection image based on the selected alignment model (p. 809, col. 2: "Once H is computed, the correction is performed on the current image".).
Therefore, the Applicant's claimed invention would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Saki to include for each subset of a plurality of subsets of the local alignment results: determining an alignment model based on the subset of the local alignment results, and evaluating the alignment model based on a fit of the alignment model to a remainder set of the local alignment results; selecting one alignment model among the plurality of alignment models based on the evaluations; and correcting a distortion of the inspection image based on the selected alignment model as taught by Marturi. The motivation/suggestion would have been to further enhance/improve the method since doing so would allow for the ability to produce a reliable model since RANSAC is exceptionally effective at ignoring erroneous data (outliers) that can severely bias conventional fitting techniques like Least Squares.
Regarding claim 2, Saki and Marturi teach: The method of claim 1, wherein evaluating the alignment model comprises: determining, in the remainder set of the local alignment results, a percentage of local alignment results that fit the alignment model (Marturi, p. 809, col. 2, "calculating the inliers". The percentage would be merely the inliers divided by the number of feature points, and as such is proportional to the number of inliers and mathematically equivalent.).
Regarding claim 3, Saki and Marturi teach: The method of claim 1, wherein the plurality of subsets are randomly selected (Marturi, RANSAC method, see page 809).
Regarding claim 4, Saki and Marturi teach: The method of claim 1, further comprising: aligning the plurality of patches of the inspection image based on the reference image; and evaluating, by a machine learning model, an alignment between a first patch of the plurality of patches and a corresponding patch of the reference image (Marturi, According to the RANSAC method as disclosed in p. 809, col. 2, four random keypoint correspondences are selected in step 1 and are used as training patches for computing a homography. The corresponding homography is considered as a "current model" (p. 809, step 3) and is used on the other keypoints to separate inliers from outliers. It is noted that, in the prior art, the Ransac method is considered as a machine learning method.).
Regarding claim 5, Saki and Marturi teach: The method of claim 4, further comprising: acquiring a training inspection image patch and a training reference image patch; and training the machine learning model to predict an alignment index between the training inspection image patch and the training reference image patch image (Marturi, According to the RANSAC method as disclosed in p. 809, col. 2, four random keypoint correspondences are selected in step 1 and are used as training patches for computing a homography. The corresponding homography is considered as a "current model" (p. 809, step 3) and is used on the other keypoints to separate inliers from outliers. It is noted that, in the prior art, the Ransac method is considered as a machine learning method.).
Regarding claim 16, Saki and Marturi teach: The method of claim 1, further comprising: estimating a first alignment model based on a first subset of the local alignment results and estimating a second alignment model based on a second subset of the local alignment results (Saki,[0015], A sixth embodiment of the present invention provides a comparative inspection device including: means for dividing and inputting two images to be processed; means for simultaneously calculating offsets for individual images input in a divided manner; means for evaluating reliability of offsets calculated for each divided image and calculating an offset for an entire image based on offsets having high reliability. See fig. 3, [0034-0038]).
Regarding claim 17, Saki and Marturi teach: The method of claim 16, further comprising: evaluating the first alignment model based on a fit of the first alignment model to a first remainder set of the local alignment results and evaluating the second alignment model based on a fit of the second alignment model to a second remainder set of the local alignment results (Saki,[0015], A sixth embodiment of the present invention provides a comparative inspection device including: means for dividing and inputting two images to be processed; means for simultaneously calculating offsets for individual images input in a divided manner; means for evaluating reliability of offsets calculated for each divided image and calculating an offset for an entire image based on offsets having high reliability. See fig. 3, [0034-0038]).
Claims 6 and 11 are rejected for reasons similar to claim 1 above.
Claims 7 and 12 are rejected for reasons similar to claim 2 above.
Claims 8 and 13 are rejected for reasons similar to claim 3 above.
Claims 9 and 14 are rejected for reasons similar to claim 4 above.
Claims 10 and 15 are rejected for reasons similar to claim 5 above.
Claim 18 is rejected for reasons similar to claim 16 above.
Claim 19 rejected for reasons similar to claim 17 above.
Claim 20 rejected for reasons similar to claims 16 and 17 above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREW H LAM whose telephone number is (571)270-7969 and fax number is 571-270-8969. The examiner can normally be reached on 9AM-5PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Benny Tieu can be reached on 571-272-7490. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ANDREW H LAM/
Primary Examiner, Art Unit 2682
Prosecution Insights