Apparatus and method for inspecting pattern

• US 20060067570A1
• Filed: 09/27/2005
• Published: 03/30/2006
• Est. Priority Date: 09/29/2004
• Status: Active Grant

• Current Assignee: SCREEN Holdings Co., Ltd.
• Original Assignee: SCREEN Holdings Co., Ltd.
• Inventors: Onishi, Hiroyuki, Asai, Hiroshi, Ogi, Hiroshi
• Granted Patent: US 7,689,029 B2
• Time in Patent Office: Days
• US Class Current: 382/147
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 7/001 using an image reference approach

Abstract

An operation part (50) in a pattern inspection apparatus (1) comprises a defect candidate image generator (511) for generating a binary defect candidate image representing a defect candidate area in an inspection image by comparing the inspection image with a reference image, in an inspection image masking part (521) the inspection image is masked with the defect candidate image to obtain a masked inspection image. In a feature value calculation part (531), an autocorrelation feature value is obtained from the masked inspection image, and outputted to a classifying part (54). The classifying part (54) comprises a classifier (541) outputting a classification result on the basis of the autocorrelation feature value and a classifier construction part (542) for constructing the classifier (541) by learning. It is thereby possible to easily perform the high accurate classification of defect candidate using the autocorrelation feature value which is hard to characterize as compared with geometric feature value or feature value representing density.

Claims

1. An apparatus for inspecting pattern on an object, comprising:

a differential image generator for generating a differential image representing a difference between a grayscale inspection image representing pattern on an object and a grayscale reference image or a difference between two images obtained from said inspection image and said reference image, respectively, or a differential image obtained from an image representing said difference;

a defect candidate image generator for generating a defect candidate image representing an area which includes a defect candidate in said inspection image by comparing said inspection image with said reference image;

a differential image masking part for masking said differential image with said defect candidate image to obtain a masked differential image;

a feature value calculation part for obtaining an autocorrelation feature value from said masked differential image; and

a classifying part for performing a classification of said defect candidate on the basis of said autocorrelation feature value.

2. The apparatus according to claim 1, further comprising an inspection image masking part for masking said inspection image with said defect candidate image to obtain a masked inspection image, wherein

said classification is also based on an autocorrelation feature value obtained from said masked inspection image.

3. The apparatus according to claim 2, further comprising

a reference image masking part for masking said reference image with said defect candidate image to obtain a masked reference image, wherein

said classification is also based on an autocorrelation feature value obtained from said masked reference image.

4. The apparatus according to claim 1, wherein

said classification is also based on an autocorrelation feature value obtained from said defect candidate image.

5. The apparatus according to claim 1, wherein

said classifying part comprises a classifier construction part for constructing a classifier by learning which outputs a classification result in accordance with autocorrelation feature value.

6. An apparatus for inspecting pattern on an object, comprising:

a defect candidate image generator for generating a defect candidate image representing an area which includes a defect candidate in a grayscale inspection image representing pattern on an object by comparing said inspection image with a reference image;

an inspection image masking part for masking said inspection image with said defect candidate image to obtain a masked inspection image;

a feature value calculation part for obtaining an autocorrelation feature value from said masked inspection image; and

a classifying part for performing a classification of said defect candidate on the basis of said autocorrelation feature value, wherein

said classifying part comprises a classifier construction part for constructing a classifier by learning which outputs a classification result in accordance with said autocorrelation feature value.

7. The apparatus according to claim 6, further comprising

a reference image masking part for masking said reference image with said defect candidate image to obtain a masked reference image, wherein

said classification is also based on an autocorrelation feature value obtained from said masked reference image.

8. The apparatus according to claim 6, wherein

said classification is also based on an autocorrelation feature value obtained from said defect candidate image.

9. A method for inspecting pattern on an object, comprising the steps of:

a) generating a differential image representing a difference between a grayscale inspection image representing pattern on an object and a grayscale reference image or a difference between two images obtained from said inspection image and said reference image, respectively, or a differential image obtained from an image representing said difference;

b) generating a defect candidate image representing an area which includes a defect candidate in said inspection image by comparing said inspection image with said reference image;

c) masking said differential image with said defect candidate image to obtain a masked differential image;

d) obtaining an autocorrelation feature value from said masked differential image; and

e) performing a classification of said defect candidate on the basis of said autocorrelation feature value.

10. The method according to claim 9, further comprising the step of

masking said inspection image with said defect candidate image to obtain a masked inspection image, wherein

said classification is also based on an autocorrelation feature value obtained from said masked inspection image.

11. The method according to claim 10, further comprising the step of

masking said reference image with said defect candidate image to obtain a masked reference image, wherein

said classification is also based on an autocorrelation feature value obtained from said masked reference image.

12. The method according to claim 9, wherein

said classification is also based on an autocorrelation feature value obtained from said defect candidate image.

13. The method according to claim 9, wherein

said classification is performed by a classifier constructed by learning which outputs a classification result in accordance with said autocorrelation feature value.

14. A method for inspecting pattern on an object, comprising the steps of:

a) generating a defect candidate image representing an area which includes a defect candidate in a grayscale inspection image representing pattern on an object by comparing said inspection image with a reference image;

b) masking said inspection image with said defect candidate image to obtain a masked inspection image;

c) obtaining an autocorrelation feature value from said masked inspection image; and

d) performing a classification of said defect candidate on the basis of said autocorrelation feature value, wherein

said classification is performed by a classifier constructed by learning which outputs a classification result in accordance with said autocorrelation feature value.

15. The method according to claim 14, further comprising the step of

masking said reference image with said defect candidate image to obtain a masked reference image, wherein

said classification is also based on an autocorrelation feature value obtained from said masked reference image.

16. The method according to claim 14, wherein

said classification is also based on an autocorrelation feature value obtained from said defect candidate image.