SYSTEM, METHOD AND COMPUTER PROGRAM PRODUCT FOR DETECTION OF DEFECTS WITHIN INSPECTION IMAGES

• US 20130336575A1
• Filed: 06/13/2012
• Published: 12/19/2013
• Est. Priority Date: 06/13/2012
• Status: Active Grant

• Current Assignee: Applied Materials Israel Limited (Applied Materials Incorporated)
• Original Assignee: Applied Materials Israel Limited (Applied Materials Incorporated)
• Inventors: Dalla-Torre, Michele, Shabat, Gil, Batikoff, Amit, Dafni, Adi
• Granted Patent: US 8,977,035 B2
• Time in Patent Office: Days
• US Class Current: 382/149
• CPC Class Codes: G06T 2207/10061 from scanning electron microscope
• CPC Class Codes: G06T 2207/20224 Image subtraction
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 7/001 using an image reference approach

Abstract

An analysis system for detection of defects within an inspection image of an inspected object, the inspection image comprising a plurality of pixels, the system including: a computerized segmentation module configured to segmentize the inspection image based on multiple anchor locations and on a mask which defines multiple mask-segments, by assigning each part out of multiple parts of the inspection image to a respective image-segment selected out of a multiple image segments, wherein the multiple image segments correspond to at least one mask-segment of said multiple mask-segments; and a defect detection processor configured to determine a presence of a defect in the inspection image based on the segmentation at least by assessing each pixel out of a plurality of pixels of the inspection image.

Claims

1. An analysis system for detection of defects within an inspection image of an inspected object, the inspection image comprising a plurality of pixels, the system comprising:

a computerized anchor processing module configured to obtain multiple anchor locations with respect to the inspection image;

a computerized segmentation module operatively coupled to the computerized anchor processing module, configured to segmentize the inspection image based on the multiple anchor locations and on a mask which defines multiple mask-segments, by assigning each part out of multiple parts of the inspection image to a respective image-segment selected out of a multiple image segments, wherein the multiple image segments correspond to at least one mask-segment of said multiple mask-segments; and

a defect detection processor operatively coupled to the computerized segmentation module, configured to determine a presence of a defect in the inspection image based on the segmentation at least by assessing each pixel out of a plurality of pixels of the inspection image based on;

(a) a result of a comparison of the pixel to correlative data of a reference image, and (b) a decision rule which depends on the image-segment selected for the pixel.

2. The system according to claim 1, wherein the anchor processing module is configured to compute the multiple anchor locations based on a matching of a template to multiple portions of the inspection image.

3. The system according to claim 2, wherein the system further comprises a reference data generator configured to downsample at least a part of a reference image of an inspected-object reference area, and to generate the template based on a result of the downsampling.

4. The system according to claim 2, wherein the system further comprises a reference data generator which is configured to generate the mask by processing a reference image which is generated from computer-aided design (CAD) data.

5. The system according to claim 1, further comprising a reference data generator which is configured to generate the mask by processing a reference image which is generated from CAD data.

6. The system according to claim 1, wherein at least two of the portions are at least partly overlapping.

7. The system according to claim 1, wherein the inspected object is selected from a group consisting of an electronic circuit, a wafer, and a photomask.

8. The system according to claim 1, wherein the anchor processing module is configured to compute the anchor locations at an accuracy which exceeds a resolution of the inspection image.

9. The system according to claim 1, wherein the processor is further configured to define different detection schemes to different areas of the inspection image based on the segmentation of at least the part of the inspection image;

wherein the defect detection processor is configured to determine the presence of the defect based on a result of the defining.

10. The system according to claim 1, further comprising a distribution analysis module configured to determine for each our of a plurality of pixels of the inspection image a distribution of the pixel with respect to one or more of the plurality of mask-segments;

wherein the computerized segmentation module is configured to assign parts of the multiple parts to one or more of the image segments based on the distributions determined for the plurality of pixels.

11. The system according to claim 1, wherein the defect detection processor is configured to classify the potential defect based on a selection of one or more image-segments to which one or more parts of the inspection image which are correlative to the potential defect where assigned, according to a classification in which classes correspond to defect types whose implications on an operability of the inspected object differ.

12. The system according to claim 1, further comprising a sensor that is configured to inspect the inspection object and to provide the inspection image based on the inspection.

13. A computerized method for detection of defects within an inspection image of an inspected object, the image comprising a plurality of pixels, the method comprising:

obtaining multiple anchor locations with respect to the inspection image;

based on the multiple anchor locations and on a mask which defines multiple mask-segments, segmentizing the inspection image by assigning each part out of multiple parts of the inspection image to a respective image-segment selected out of a multiple image-segments, wherein the multiple image-segments correspond to at least one mask-segment of said multiple mask-segments; and

determining a presence of a defect in the inspection image based on the segmentation, the determining of the presence of the defect comprises;

for each pixel out of a plurality of pixels of the inspection image, assessing the pixel based on;

(a) a result of a comparison of the pixel to correlative data of a reference image, and (b) a decision rule which depends on the image-segment selected for the pixel.

14. The method according to claim 13, wherein the obtaining comprises computing the multiple anchor locations based on a matching of a template to multiple portions of the inspection image.

15. The method according to claim 13, wherein the determining of the presence of the defect is based on different detection schemes defined for different areas of the inspection image, wherein the defining is based on the segmentation.

16. The method according to claim 13, further comprising generating the mask by processing a reference image which is generated from CAD data.

17. A computer readable storage medium including instructions that, when executed by a processing system, cause the processing system to perform a method for classifying a potential defect identified within an inspection image of an inspected object, the method comprising:

obtaining multiple anchor locations with respect to the inspection image;

based on the multiple anchor locations and on a mask which defines multiple mask-segments, segmentizing the inspection image by assigning each part out of multiple parts of the inspection image to a respective image-segment selected out of a multiple image-segments, wherein the multiple image-segments correspond to at least one mask-segment of said multiple mask-segments; and

determining a presence of a defect in the inspection image based on the segmentation, the determining of the presence of the defect comprises;

for each pixel out of a plurality of pixels of the inspection image, assessing the pixel based on;

(a) a result of a comparison of the pixel to correlative data of a reference image, and (b) a decision rule which depends on the image-segment selected for the pixel.

18. The computer readable storage medium according to claim 17, wherein the obtaining comprises computing the multiple anchor locations based on a matching of a template to multiple portions of the inspection image.

19. The computer readable storage medium according to claim 17, wherein the method further comprises generating the template, wherein the generating comprises downsampling at least a part of a reference image of an inspected-object reference area.

20. The computer readable storage medium according to claim 17, wherein the determining of the presence of the defect is based on different detection schemes defined for different areas of the inspection image, wherein the defining is based on the segmentation.