System and method for patch based inspection

Patent metadata

Field	Value
Publication number	US-9904995-B2
Application number	US-201514964527-A
Country	US
Kind code	B2
Filing date	Dec 9, 2015
Priority date	Dec 9, 2015
Publication date	Feb 27, 2018
Grant date	Feb 27, 2018

Abstract

An inspection system that may include a processor and a memory module; wherein the memory module is configured to store a first image of an area of an object and a second image of the area of the object; wherein the processor is configured to generate a synthetic image of the area of the object, and to compare the synthetic image to the second image to provide defect detection results.

First claim

We claim:

1. An inspection system, comprising:
a memory to store a first image of an area of an object and a second image of the area of the object; and
a processor operably coupled to the memory, wherein the processor is to:
generate a synthetic image of the area of the object by repeating, for each first patch out of a group of first patches that belong to the first image, the operations of:
(i) searching for relevant reference patches, wherein each relevant reference patch has a reference patch signature that is similar to a first patch signature of the first patch; and
(ii) in response to detecting the relevant reference patches, processing the relevant reference patches to provide a synthetic patch of the synthetic image, wherein the synthetic image is generated such that a size of the synthetic image and a size of the first image are the same; and

compare the synthetic image to the second image to provide defect detection results.

2. A method for inspecting an area of an object, the method comprises:
generating, by a processor, a synthetic image of the area of the object, wherein generating the synthetic image comprises repeating, for each first patch out of a group of first patches that belong to a first image of the object, the operations of:
(i) searching for relevant reference patches, wherein each relevant reference patch has a reference patch signature that is similar to a first patch signature of the first patch; and
(ii) in response to detecting the relevant reference patches, processing the relevant reference patches to provide a synthetic patch of the synthetic image, wherein the synthetic image is generated such that a size of the synthetic image and a size of the first image are the same; and

comparing the synthetic image to a second image of the object to provide defect detection results.

3. The method according to claim 2 , wherein generating the synthetic image further comprising positioning the synthetic patch at a synthetic patch location that corresponds to a location of the first patch.

4. The method according to claim 3 , wherein generating the synthetic image further comprises applying a smoothing function on partially overlapping synthetic patches.

5. The method according to claim 2 , wherein generating the synthetic image further comprising receiving or generating information about regions of interest within the area of the object; and wherein the group of first patches includes only first patches that are at least partially included within a first region of interest of the regions of interest.

6. The method according to claim 5 , wherein the object is a lithographic mask and wherein the regions of interest correspond to a printability of regions of the lithographic mask.

7. The method according to claim 2 , wherein generating the synthetic image further comprises generating of the synthetic patch by calculating a weighted sum of the relevant reference patches.

8. The method according to claim 2 , wherein the first patch signature comprises information about intensities of pixels of the first patch and information about intensities of pixels of a second image region; and wherein the second image region is located, within the second image, at a second image region location that that is proximate to a second image location that corresponds to a first location of the first patch.

9. The method according to claim 8 , wherein the second image region surrounds second image pixels that are located, in the second image, at the second image location that corresponds to the first location of the first patch.

10. The method according to claim 8 , comprising determining a similarity between the first patch signature and the reference patch signature based on a distance between the first patch signature and the reference patch signature.

11. The method according to claim 8 , wherein the first patch signature further comprises spatial relationship information about a spatial relationship between the first patch and an anchor.

12. A non-transitory computer readable medium that stores instructions that once executed by a processing device cause the processing device to:
generate a synthetic image of an area of an object, wherein generating the synthetic image comprises repeating, for each first patch out of a group of first patches that belong to a first image of the object, the operations of:
(i) searching for relevant reference patches, wherein each relevant reference patch has a reference patch signature that is similar to a first patch signature of the first patch; and
(ii) in response to detecting the relevant reference patches, processing the relevant reference patches to provide a synthetic patch of the synthetic image, wherein the synthetic image is generated such that a size of the synthetic image and a size of the first image are the same; and

compare the synthetic image to a second image of the object to provide defect detection results.

13. The non-transitory computer readable medium according to claim 12 , wherein the instructions further cause the processing device to position the synthetic patch at a synthetic patch location that corresponds to a location of the first patch.

14. The non-transitory computer readable medium according to claim 13 , wherein the instructions further cause the processing device to apply a smoothing function on partially overlapping synthetic patches.

Assignees

• Applied Materials Israel Ltd
• Applied Materials Israel Ltd

Inventors

• Karlinsky Leonid
• Rosenweig Moshe
• Cohen Boaz

Classifications

• G06V10/7557

  based on appearance, e.g. active appearance models [AAM] · CPC title

• G06T7/0081

  Physics · mapped topic

• G06K2209/19

  Physics · mapped topic

• G06T5/002

  Physics · mapped topic

• G06T7/001 Primary

  using an image reference approach · CPC title