# US 10,504,692 B2 · Method and system for generating a synthetic image of a region of an object > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,504,692 B2 - Document ID: US10504692B2 - Status: Granted - Kind: B2 - Application number: 16/052,094 - Filed: 2018-08-01 - Published: 2019-02-07 - Granted: 2019-12-10 - Earliest claimed: 2017-08-07 - Assignees: Applied Materials Israel Ltd. - Applicants: Applied Materials Israel Ltd. - Inventors: Zeev Zohar - Web page: https://patentgrep.com/patent/US10504692B2 ## CPC - H01J 37/222: {Image processing arrangements associated with the tube} - G06F 18/21345: {enforcing sparsity or involving a domain transformation} - G06F 18/28: Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries - G06N 20/00: Machine learning - G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods} - G06V 10/772: Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries - G06V 20/695: {Preprocessing, e.g. image segmentation} - G06V 10/513: {Sparse representations} - H01J 2237/221: Image processing - H01J 2237/226: Image reconstruction - H01J 2237/24495: Signal processing, e.g. mixing of two or more signals - H01J 2237/28: Scanning microscopes - H01J 2237/2802: Transmission microscopes - H01J: ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS (spark-gaps H01T; electric arc lamps H05B31/00; particle accelerators H05H) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method for generating a synthetic image of a region of an object, includes: generating, by a charged particle microscope, a charged particle microscope image of the region of the object; calculating a sparse representation of the charged particle microscope image; wherein the sparse representation of the charged particle microscope image comprises multiple first atoms; generating the synthetic image of the region, wherein the synthetic image of the region is formed from multiple second atoms; wherein the generating of the synthetic image of the region is based on a mapping between the multiple first atoms and the multiple second atoms; wherein the charged particle microscope image and the multiple first atoms are of a first resolution; and wherein the synthetic image of the region and the multiple second atoms are of a second resolution that is finer than the first resolution. ## Claims ### Claim 1 A method for generating a synthetic image of a region of an object, the method comprising: generating, by a charged particle microscope, a charged particle microscope image of the region of the object; calculating a sparse representation of the charged particle microscope image; wherein the sparse representation of the charged particle microscope image comprises multiple first atoms; generating the synthetic image of the region, wherein the synthetic image of the region is formed from multiple second atoms; wherein the generating of the synthetic image of the region is based on a mapping between the multiple first atoms and the multiple second atoms; wherein the charged particle microscope image and the multiple first atoms are of a first resolution; and wherein the synthetic image of the region and the multiple second atoms are of a second resolution that is finer than the first resolution. ### Claim 2 (depends on 1) The method according to claim 1 wherein the generating of the charged particle microscope image is preceded by performing a dictionary learning process for generating at least one dictionary that comprises the multiple first atoms and the multiple second atoms. ### Claim 3 (depends on 2) The method according to claim 2 wherein the performing of the dictionary learning process comprises acquiring first resolution charged particle microscope images of a reference object and acquiring a second resolution charged particle microscope images of the reference object. ### Claim 4 (depends on 1) The method according to claim 1 wherein the generating of the charged particle microscope image is preceded by receiving at least one dictionary that comprises the multiple first atoms and the multiple second atoms. ### Claim 5 (depends on 1) The method according to claim 1 wherein the generating of the charged particle microscope image is preceded by performing a dictionary learning process for generating at least one dictionary that comprises multiple first atoms that are related to multiple perspectives of the charged particle microscope and multiple second atoms that are related to the multiple perspectives of the charged particle microscope. ### Claim 6 (depends on 5) The method according to claim 5 wherein the performing of the dictionary learning process comprises calculating a mapping between first atoms and second atoms that are related to different perspectives. ### Claim 7 (depends on 5) The method according to claim 5 wherein the charged particle microscope image is related to a certain perspective of the charged particle microscope and wherein the calculating of the sparse representation of the charged particle microscope image is based on at least one first atom that is related to another perspective of the charged particle microscope. ### Claim 8 (depends on 5) The method according to claim 5 wherein the charged particle microscope image is related to a certain perspective of the charged particle microscope and wherein the calculating of the sparse representation of the charged particle microscope image is based on first atoms related to at least two perspectives out of the multiple perspectives. ### Claim 9 (depends on 5) The method according to claim 5 wherein the charged particle microscope image is related to a certain perspective of the charged particle microscope and wherein the synthetic image is related to another perspective. ### Claim 10 (depends on 1) The method according to claim 1 wherein the generating of the charged particle microscope image is preceded by receiving one or more dictionaries that are related to multiple perspectives of the charged particle microscope. ### Claim 11 (depends on 1) The method according to claim 1 wherein the charged particle microscope image comprises multiple charged particle microscope patches; wherein the calculating of the sparse representation of the charged particle microscope image comprises calculating sparse representations of the multiple charged particle microscope patches; and wherein the generating of the synthetic image comprises generating multiple synthetic image patches. ### Claim 12 (depends on 11) The method according to claim 11 comprising calculating a confidence attribute for each synthetic image patch of the multiple synthetic image patches. ### Claim 13 (depends on 12) The method according to claim 12 wherein a confidence attribute of a given synthetic image patch of the multiple synthetic image patches is associated with a number of different second atoms that are included in the given synthetic image patch. ### Claim 14 (depends on 1) The method according to claim 1 comprising detecting a suspected defect in the region based on a number of different second atoms that form an element of the synthetic image. ### Claim 15 (depends on 1) The method according to claim 1 wherein the region of the object is an edge region of the object. ### Claim 16 A method for defect detection, the method comprises: generating, by a charged particle microscope, a charged particle microscope image of a region of an object; calculating a sparse representation of the charged particle microscope image; wherein the sparse representation of the charged particle microscope image comprises multiple first atoms; and evaluating an existence of a suspected defect in the region based on a number of different first atoms that form an element of the sparse representation of the charged particle microscope image, wherein evaluating the existence of the suspected defect includes calculating the number of different first atoms of each element of the sparse representation. ### Claim 17 A computer program product that stores instructions that once executed by a charged particle microscope cause the charged particle microscope to perform steps comprising: generate a charged particle microscope image of a region of an object; calculate a sparse representation of the charged particle microscope image; wherein the sparse representation of the charged particle microscope image comprises multiple first atoms; and generate a synthetic image of the region, wherein the synthetic image of the region is formed from multiple second atoms; wherein a generating of the synthetic image of the region is based on a mapping between the multiple first atoms and the multiple second atoms; wherein the charged particle microscope image and the multiple first atoms are of a first resolution; and wherein the synthetic image of the region and the multiple second atoms are of a second resolution that is finer than the first resolution. ### Claim 18 A charged particle microscope, comprising: charged particle optics; at least one charged particle detector; and a processor; wherein the charged particle optics and the at least one charged particle detector are configured to generate a charged particle microscope image of a region of an object; wherein the processor is configured to: calculate a sparse representation of the charged particle microscope image; wherein the sparse representation of the charged particle microscope image comprises multiple first atoms; and generate a synthetic image of the region, wherein the synthetic image of the region is formed from multiple second atoms; wherein a generating of the synthetic image of the region is based on a mapping between the multiple first atoms and the multiple second atoms; wherein the charged particle microscope image and the multiple first atoms are of a first resolution; and wherein the synthetic image of the region and the multiple second atoms are of a second resolution that is finer than the first resolution.