METHOD OF RECOGNIZING WAFER

• US 20180197284A1
• Filed: 01/12/2017
• Published: 07/12/2018
• Est. Priority Date: 01/12/2017
• Status: Active Grant

• Current Assignee: Nanya Technology Corporation
• Original Assignee: Nanya Technology Corporation
• Inventors: FANG, WEI-LI
• Granted Patent: US 10,147,178 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/2135 based on approximation criteria, e.g. principal component analysis
• CPC Class Codes: G06F 18/24147 Distances to closest patterns, e.g. nearest neighbour classification
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/7715 Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods

Abstract

A method includes obtaining image information including a first vector by capturing an image of a first wafer, wherein the first wafer is known to be a good product; obtaining image information including a second vector by capturing an image of a second wafer, wherein the second wafer is known to be a defective product; calculating a projection vector based on a covariance matrix associated with the first vector and the second vector; obtaining image information including a third vector by capturing an image of a third wafer under a test; projecting each of the first vector, the second vector and the third vector onto the projection vector; and classifying the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector.

Claims

1. A method, comprising:

obtaining image information including a first vector by capturing an image of a first wafer, wherein the first wafer is known to be a good product;

obtaining image information including a second vector by capturing an image of a second wafer, wherein the second wafer is known to be a defective product;

calculating a projection vector based on a covariance matrix associated with the first vector and the second vector;

obtaining image information including a third vector by capturing an image of a third wafer under a test;

projecting each of the first vector, the second vector and the third vector onto the projection vector; and

classifying the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector.

2. The method of claim 1, wherein the calculation of the projection vector based on the covariance matrix associated with the first vector and the second vector further comprises:

calculating the covariance matrix based on the first vector and the second vector.

3. The method of claim 2, wherein the calculation of the projection vector based on the covariance matrix associated with the first vector and the second vector further comprises:

calculating a first eigenvalue and a second eigenvalue based on the covariance matrix.

4. The method of claim 3, wherein the calculation of the projection vector based on the covariance matrix associated with the first vector and the second vector further comprises:

calculating a first eigenvector and a second eigenvector based on both the first eigenvalue and the second eigenvalue.

5. The method of claim 4, wherein the calculation of the projection vector based on the covariance matrix associated with the first vector and the second vector further comprises:

calculating the projection vector based on both the first eigenvector and the second eigenvector.

6. The method of claim 1, wherein the classification of the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector comprises:

classifying the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector and according to the nearest neighbor rule (NNR).

7. The method of claim 1, wherein the classification of the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector comprises:

calculating a first distance between the projected first vector and the projected third vector;

calculating a second distance between the projected first vector and the projected third vector; and

classifying the third wafer as either the good product or the defective product based on the first distance and the second distance.

8. The method of claim 7, wherein the classification of the third wafer as either the good product or the defective product based on the first distance and the second distance comprises:

classifying the third wafer as the good product when the first difference is less than the second difference.

9. The method of claim 7, wherein the classification of the third wafer as either the good product or the defective product based on the first distance and the second distance comprises:

classifying the third wafer as the defective product when the first difference is greater than the second difference.

10. A method, comprising:

obtaining image information including a first vector by capturing an image of a first wafer, wherein the first wafer is known to be a good product;

obtaining image information including a second vector by capturing an image of a second wafer, wherein the second wafer is known to be a defect product;

calculating a covariance matrix based on the first vector and the second vector;

calculating a first eigenvalue and a second eigenvalue based on the covariance matrix;

comparing the first eigenvalue and the second eigenvalue;

calculating an eigenvector based on the first eigenvalue, instead of on both the first eigenvalue and the second eigenvalue when the first eigenvalue is greater than the second eigenvalue;

obtaining a projection vector based on the eigenvector;

projecting each of the first vector, the second vector and the third vector onto the projection vector; and

classifying the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector.

11. The apparatus of claim 10, wherein the classification of the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector comprises:

classifying the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector and according to the nearest neighbor rule (NNR).

12. The apparatus of claim 10, wherein the classification of the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector comprises:

calculating a first distance between the projected first vector and the projected third vector;

calculating a second distance between the projected first vector and the projected third vector; and

classifying the third wafer as either the good product or the defective product based on the first distance and the second distance.

13. The apparatus of claim 12, wherein the classification of the third wafer as either the good product or the defective product based on the first distance and the second distance comprises:

classifying the third wafer as the good product when the first difference is less than the second difference.

14. The apparatus of claim 12, wherein the classification of the third wafer as either the good product or the defective product based on the first distance and the second distance comprises:

classifying the third wafer as the defective product when the first difference is greater than the second difference.

15. An apparatus, comprising:

an image capturing device configured to capture an image of a first wafer, an image of a second wafer and an image of a third wafer, wherein the first wafer is known to be a good product, the second wafer is known to be a defective product, and the third wafer is under a test; and

a processing device configured to;

obtain image information including a first vector based on the image of the first wafer;

obtain image information including a second vector based on the image of the second wafer;

obtain image information including a third vector based on the image of the third wafer;

calculate a projection vector based on a covariance matrix associated with the first vector and the second vector;

project each of the first vector, the second vector and the third vector onto the projection vector; and

classify the third wafer as either the good product or the defective product based on the projected first vector, the projected second vector and the projected third vector.

16. The apparatus of claim 15, wherein the processing device is further configured to calculate the covariance matrix based on the first vector and the second vector.

17. The apparatus of claim 16, wherein the processing device is further configured to calculate a first eigenvalue and a second eigenvalue based on the covariance matrix.

18. The apparatus of claim 17, wherein the processing device is further configured to calculate a first eigenvector and a second eigenvector based on both the first eigenvalue and the second eigenvalue.

19. The apparatus of claim 18, wherein the processing device is further configured to calculate the projection vector based on both the first eigenvector and the second eigenvector.