Iterative defect filtering process

• US 10,049,441 B2
• Filed: 02/09/2016
• Issued: 08/14/2018
• Est. Priority Date: 10/23/2014
• Status: Active Grant

• Current Assignee: Applied Materials Israel Limited (Applied Materials Incorporated)
• Original Assignee: Applied Materials Israel Limited (Applied Materials Incorporated)
• Inventors: Shabtay, Saar, Kaizerman, Idan, Wachs, Amir
• Primary Examiner(s): Wu, Jingge
• Application Number:
  US15/019,894
• Publication Number:
  US 20160163038A1
• Time in Patent Office: 917 Days
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/20112 Image segmentation details
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 30/248 involving plural approaches, e.g. verification by template match; Resolving confusion among similar patterns, e.g. "O" versus "Q" G06V30/242 takes precedence

Abstract

A method for classifying defects of a wafer, the method is executed by a computerized system, the method may include obtaining defect candidate information about a group of defect candidates, wherein the defect candidate information comprises values of attributes per each defect candidate of the group; selecting, by a processor of the computerized system, a selected sub-group of defect candidates in response to values of attributes of defect candidates that belong to at least the selected sub-group; classifying defect candidates of the selected sub-group to provide selected sub-group classification results; repeating, until fulfilling a stop condition: selecting an additional selected sub-group of defect candidates in response to (a) values of attributes of defect candidates that belong to at least the additional selected sub-group; and (b) classification results obtained from classifying at least one other selected sub-group; and classifying defect candidates of the additional selected sub-group to provide additional selected sub-group classification results.

Claims

1. A method comprising:

obtaining defect candidate information of a group of defect candidates, wherein the defect candidate information comprises values of attributes for each defect candidate of the group of defect candidates;

selecting, by a processing device, a sub-group of defect candidates from the group of defect candidates to be analyzed in a first iteration of a semiconductor defect classification operation, the sub-group of defect candidates being selected based on the values of attributes of defect candidates that belong to the selected sub-group;

receiving classification results of the selected sub-group of defect candidates from the first iteration of the semiconductor defect classification operation;

selecting an additional sub-group from the group of defect candidates to be analyzed in a second iteration of the semiconductor defect classification operation, the additional sub-group of defect candidates being selected based on the values of attributes of defect candidates that belong to the additional selected sub-group and classification results of the sub-group that were previously received from the first iteration of the semiconductor defect classification operation; and

receiving classification results of the selected additional sub-group of defect candidates from the second iteration of the semiconductor defect classification operation.

2. The method of claim 1, further comprising:

transmitting, to a defect classifier, information of the selected sub-group of defect candidates, wherein the receiving of the classification results of the selected sub-group of defect candidates is from the defect classifier and is based on defect candidate information of each defect candidate of the selected sub-group of defect candidates.

3. The method of claim 1, wherein the obtaining of the defect candidate information comprises receiving the defect candidate information from an optical inspection tool.

4. The method of claim 1, wherein the receiving of the classification results of the selected sub-group of defect candidates comprises classifying the selected sub-group of defect candidates based on an automatic defect classification.

5. The method of claim 1, further comprising:

receiving review results from an inspection and review tool associated with the obtaining of the defect candidate information.

6. The method of claim 1, further comprising:

receiving review results from a review tool that comprises an automatic defect classifier providing the classification results and a device performing the selecting of the sub-group of defect candidates.

7. The method of claim 1 wherein the receiving of the classification results of the selected sub-group of defect candidates comprises:

imaging the defect candidates of the selected sub-group by a charged particle beam to generate charged particle images; and

processing the charged particle images by a defect classifier to provide the selected sub-group classification results.

8. The method of claim 1, wherein subsequent iterations of the the semiconductor defect classification operation until a fulfilling of a stop condition that corresponds to receiving classification results having a purity level that exceeds a purity threshold.

9. The method of claim 8, further comprising:

obtaining one or more images of each defect candidate of each selected sub-group, wherein the stop condition is fulfilled when a threshold number of images corresponding to a particular defect type have been obtained.

10. A system comprising:

a memory; and

a processing device coupled with the memory to;

obtain defect candidate information of a group of defect candidates, wherein the defect candidate information comprises values of attributes for each defect candidate of the group of defect candidates;

select a sub-group of defect candidates from the group of defect candidates to be analyzed in a first iteration of a semiconductor defect classification operation, the sub-group of defect candidates being selected based on the values of attributes of defect candidates that belong to the selected sub-group;

receive classification results of the selected sub-group of defect candidates from the first iteration of the semiconductor defect classification operation;

select an additional sub-group from the group of defect candidates to be analyzed in a second iteration of the semiconductor defect classification operation, the additional sub-group of defect candidates being selected based on the values of attributes of defect candidates that belong to the additional selected sub-group and classification results of the sub-group that were previously received from the first iteration of the semiconductor defect classification operation; and

receive classification results of the selected additional sub-group of defect candidates from the second iteration of the semiconductor defect classification operation.

11. The system of claim 10, wherein the processing device is further to:

transmit, to a defect classifier, information of the selected sub-group of defect candidates, wherein the receiving of the classification results of the selected sub-group of defect candidates is from the defect classifier and is based on defect candidate information of each defect candidate of the selected sub-group of defect candidates.

12. The system of claim 10, wherein to obtain the defect candidate information, the processing device is further to receive the defect candidate information from an optical inspection tool.

13. The system of claim 10, wherein to receive the classification results of the selected sub-group of defect candidates, the processing device is further to classify the selected sub-group of defect candidates based on an automatic defect classification.

14. The system of claim 10, wherein the processing device is further to:

receive review results from an inspection and review tool associated with the obtaining of the defect candidate information.

15. A non-transitory computer readable medium comprising instructions that, when executed by a processing device, cause the processing device to:

obtain defect candidate information of a group of defect candidates, wherein the defect candidate information comprises values of attributes for each defect candidate of the group of defect candidates;

select a sub-group of defect candidates from the group of defect candidates to be analyzed in a first iteration of a semiconductor defect classification operation, the sub-group of defect candidates being selected based on the values of attributes of defect candidates that belong to the selected sub-group;

receive classification results of the selected sub-group of defect candidates from the first iteration of the semiconductor defect classification operation;

select an additional sub-group from the group of defect candidates to be analyzed in a second iteration of the semiconductor defect classification operation, the additional sub-group of defect candidates being selected based on the values of attributes of defect candidates that belong to the additional selected sub-group and classification results of the sub-group that were previously received from the first iteration of the semiconductor defect classification operation; and

receive classification results of the selected additional sub-group of defect candidates from the second iteration of the semiconductor defect classification operation.

16. The non-transitory computer readable medium of claim 15, wherein the processing device is further to:

transmit, to a defect classifier, information of the selected sub-group of defect candidates, wherein the receiving of the classification results of the selected sub-group of defect candidates is from the defect classifier and is based on defect candidate information of each defect candidate of the selected sub-group of defect candidates.

17. The non-transitory computer readable medium of claim 15, wherein to obtain the defect candidate information, the processing device is to receive the defect candidate information from an optical inspection tool.

18. The non-transitory computer readable medium of claim 15, wherein to receive the classification results of the selected sub-group of defect candidates, the processing device is further to classify the selected sub-group of defect candidates based on an automatic defect classification.

19. The non-transitory computer readable medium of claim 15, wherein the processing device is further to:

receive review results from an inspection and review tool associated with the obtaining of the defect candidate information.