Automatic defect classification

Patent metadata

Field	Value
Publication number	US-11300521-B2
Application number	US-201816619941-A
Country	US
Kind code	B2
Filing date	Jun 14, 2018
Priority date	Jun 14, 2017
Publication date	Apr 12, 2022
Grant date	Apr 12, 2022

Abstract

A method for automatic defect classification, the method may include (i) acquiring, by a first camera, at least one first image of at least one area of an object; (ii) processing the at least one first image to detect a group of suspected defects within the at least one area; (iii) performing a first classification process for initially classifying the group of suspected defects; (iii) determining whether a first subgroup of the suspected defects requires additional information from a second camera for a completion of a classification; (iv) when determining that the first subgroup of the suspected defects requires additional information from the second camera then: (a) acquiring second images, by the second camera, of the first subgroup of the suspected defects; and (b) performing a second classification process for classifying the first subgroup of suspected defects.

First claim

We claim:

1. A method for automatic defect classification, the method comprises:
acquiring, by a first camera, at least one first image of at least one area of an object;
processing the at least one first image to detect a group of suspected defects within the at least one area;
performing a first classification process for initially classifying the group of suspected defects;
determining whether a first subgroup of the suspected defects requires additional information from a second camera for a completion of a classification;
wherein the determining is responsive to:
(a) a criticality of the suspected defects;
(b) an accuracy of the first classification process; and
(c) difference between a reliability, related to a type of suspected defect, of the first classification process and a reliability, related to a type of suspected defect, of the second classification process; wherein the reliability is reflected by a success rate, a false alarm rate and false positive rate;
when determining that the first subgroup of the suspected defects requires additional information from the second camera then:
acquiring second images, by the second camera, of the first subgroup of the suspected defects; and
performing a second classification process for classifying the first subgroup of suspected defects.

2. The method according to claim 1 comprising acquiring the second images without acquiring images of suspected defects that do not belong to the first subgroup of suspected defects.

3. The method according to claim 1 wherein a throughput of the first camera exceeds a throughput of the second camera.

4. The method according to claim 1 wherein a resolution of the first camera is coarser than resolution of the second camera.

5. The method according to claim 1 wherein the first camera is a black and white camera and the second camera is selected out of an infrared camera, a near infrared camera and a three dimension profiler.

6. The method according to claim 1 comprising maintaining the wafer on a chuck during the acquiring of the at least one first image, during the acquiring of the second images, and between the acquiring of the at least one first image and the acquiring of the second images.

7. The method according to claim 1 wherein the determining is responsive to a difference between image acquisition parameters of the first camera and second camera.

8. The method according to claim 1 wherein the determining is responsive to the criticality of the suspected defects.

9. The method according to claim 1 wherein the determining is responsive to the accuracy of the first classification process.

10. The method according to claim 1 wherein the determining is executed without human intervention.

11. The method according to claim 1 wherein the determining is responsive to the difference between the reliability, related to the type of suspected defect, of the first classification process and a reliability, related to the type of suspected defect, of the second classification process.

12. A non-transitory computer program product that stores instructions that once executed by a computerized system cause the computerized system to execute the steps of:
acquiring, by a first camera, at least one first image of at least one area of an object;
processing the at least one first image to detect a group of suspected defects within the at least one area;
performing a first classification process for initially classifying the group of suspected defects;
determining whether a first subgroup of the suspected defects requires additional information from a second camera for a completion of a classification;
wherein the determining is responsive to:
(a) a criticality of the suspected defects;
(b) an accuracy of the first classification process; and
(c) difference between a reliability, related to a type of suspected defect, of the first classification process and a reliability, related to a type of suspected defect, of the second classification process; wherein the reliability is reflected by a success rate, a false alarm rate and false positive rate;
when determining that the first subgroup of the suspected defects requires additional information from the second camera then:
acquiring second images, by the second camera, of the first subgroup of the suspected defects; and
performing a second classification process for classifying the first subgroup of suspected defects.

13. The non-transitory computer readable medium according to claim 12 that stores instructions for acquiring the second images without acquiring images of suspected defects that do not belong to the first subgroup of suspected defects.

14. The non-transitory computer readable medium according to claim 12 wherein a throughput of the first camera exceeds a throughput of the second camera.

15. The non-transitory computer readable medium according to claim 12 wherein a resolution of the first camera is coarser than resolution of the second camera.

16. The non-transitory computer readable medium according to claim 12 wherein the first camera is a black and white camera and the second camera is selected out of an infrared camera, a near infrared camera and a three dimension profiler.

17. The non-transitory computer readable medium according to claim 12 that stores instructions for maintaining the wafer on a chuck during the acquiring of the at least one first image, during the acquiring of the second images, and between the acquiring of the at least one first image and the acquiring of the second images.

18. The non-transitory computer readable medium according to claim 12 wherein the determining is responsive to a difference between image acquisition parameters of the first camera and second camera.

19. The non-transitory computer readable medium according to claim 12 wherein the determining is responsive to a criticality of the suspected defects.

20. The non-transitory computer readable medium according to claim 12 wherein the determining is responsive to an accuracy of the first classification process.

21. The non-transitory computer readable medium according to claim 12 wherein the determining is executed without human intervention.

22. The non-transitory computer readable medium according to claim 12 wherein the determining is responsive to difference between a reliability, related to a type of suspected defect, of the first classification process and a reliability, related to a type of suspected defect, of the second classification process.

23. A system for automatic defect classification, the system comprises:
a first camera that is constructed and arranged to acquire at least one first image of at least one area of an object;
a second camera;
at least one processor that is constructed and arranged to (i) process the at least one first image to detect a group of suspected defects within the at least one area; (ii) perform a first classification process for initially classifying the group of suspected defects; and (iii) determine whether a first subgroup of the suspected defects requires additional information from a second camera for a completion of a classification;
wherein the determining is responsive to:
(a) a criticality of the suspected defects;
(b) an accuracy of the first classification process;
(c) difference between a reliability, related to a type of suspected defect, of the first classification process and a reliability, related to a type of suspected defect, o

Assignees

• Camtek Ltd

Inventors

• Regensburger Menachem
• Buzaglo Daniel

Classifications

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G01N2021/8887

  based on image processing techniques · CPC title

• G01N2021/8854

  Grading and classifying of flaws · CPC title

• G06T2207/30148

  Semiconductor; IC; Wafer · CPC title

• G06T7/66

  of image moments or centre of gravity · CPC title