Machine vision methods and system for boundary point-based comparison of patterns and images

• US 6,381,366 B1
• Filed: 12/18/1998
• Issued: 04/30/2002
• Est. Priority Date: 12/18/1998
• Status: Expired due to Term

• Current Assignee: Cognex Corporation
• Original Assignee: Cognex Corporation
• Inventors: Taycher, Leonid, Garakani, Arman
• Primary Examiner(s): Johns, Andrew W.
• Assistant Examiner(s): AZARIAN, SEYED H
• Application Number:
  US09/215,943
• Time in Patent Office: 1,229 Days
• Field of Search: 382/199, 382/198, 382/200, 382/201, 382/202, 382/203, 382/204, 382/152, 382/151
• US Class Current: 382/199
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 2207/30152 Solder
• CPC Class Codes: G06T 7/33 using feature-based methods

Abstract

The invention provides boundary-based machine vision methods and systems for comparing a pattern to an image. These contemplate the steps of finding boundary points in the image and comparing those points with boundary points in the pattern to identify “matches,” i.e., boundary points in the image that match boundary points in the pattern, “extras,” i.e., boundary points in the image which do not match boundary points in the pattern, and “missing,” i.e., boundary points in the pattern that do not match boundary points in the image. Quantitative and/or qualitative information about matching, extra or missing points can be generated, including the differences between the locations, angles and contrasts of each boundary point in the image and the corresponding boundary point in the pattern.

Claims

1. In a machine vision method for comparing a pattern and an image, the improvement comprising:

A. finding points on a boundary in the image,

B. for each point on the boundary in the image, determining whether there exists a matching point on a boundary in the pattern,

C. for each point on the boundary in the image for which there exists a matching point on the boundary in pattern, determining any of a qualitative and a quantitative relationship between those matching points, and

D. generating a list identifying the points on the boundary in the image for which there exist matching points on the boundary in the pattern and identifying any of the qualitative and quantitative relationships between those matching points.

2. In a method according to claim 1, the further improvement comprising generating a list identifying points on the boundary in the image for which there do not exist matching points on the boundary in the pattern.

3. In a method according to claim 2, the further improvement comprising generating a list identifying points on the boundary in the pattern for which there do not exist matching points on the boundary in the image.

4. In a method according to claim 1, the further improvement wherein step (C) includes determining any of

(i) a distance relationship,

(ii) a direction relationship,

(iii) a contrast relationship,

between at least a selected point on the boundary in the image and the matching point on the boundary in the pattern.

5. In a method according to claim 4, the further improvement wherein step (D) includes generating the list so as to include any of the distance relationship, direction relationship, and contrast relationship between the matching points.

6. In a method according to claim 5, the further improvement wherein step (B) includes determining a distance between a point on the boundary in the image and a point on the boundary in the pattern.

7. In a method according to claim 6, the further improvement wherein step (B) includes identifying as corresponding a point on the boundary in the image that lies within a selected distance of a point on the boundary in the pattern.

8. In a machine vision method for comparing a pattern and an image, the improvement comprising:

A. finding points on a boundary in the image,

B. for each point on the boundary in the image, determining whether there exists a matching point on a boundary in the pattern,

C. generating a list identifying the points on the boundary in the image for which there exist matching points on the boundary in the pattern,

D. generating a list identifying points on the boundary in the image for which there do not exist matching points on the boundary in the pattern, and

E. generating a list identifying points on the boundary in the pattern for which there do not exist matching points on the boundary in the image.

9. In a method according to claim 8, the further improvement wherein step (C) includes determining, for each point on the boundary in the image for which there exists a matching point on the boundary in the pattern, any of a qualitative and a quantitative relationship between those matching points.

10. In a method according to claim 9, the further improvement wherein step (C) includes generating a list identifying the points on the boundary in the image for which there exist matching points on the boundary in the pattern and identifying any of the qualitative and quantitative relationships between those matching points.

11. In a method according to claim 10, the further improvement wherein step (C) includes determining any of

(i) a distance relationship,

(ii) a direction relationship,

(iii) a contrast relationship,

between at least a selected point on the boundary in the image and the matching point on the boundary in the pattern, and wherein step (C) further includes generating the list so as to include any of the distance relationship, direction relationship, and contrast relationship between the matching points.

12. In a method according to claim 11, the further improvement wherein step (C) includes identifying as corresponding a point on the boundary in the image that lies within a selected distance of a point on the boundary in the pattern.

13. In a machine vision system, the improvement for comparing a pattern and an image comprising performing the steps of:

A. finding points on a boundary in the image,

B. finding points on a boundary in the pattern,

C. for each point on the boundary in the image, determining whether there exists a matching point on the boundary in the pattern,

D. for each point on the boundary in the image for which there exists a matching point on the boundary in the pattern, determining any of a qualitative and a quantitative relationship between those matching points, and

E. generating a list identifying the points on the boundary in the image for which there exist matching points on the boundary in the pattern and identifying any of the qualitative and quantitative relationships between those matching points.

14. In a system according to claim 13, the further improvement wherein the machine vision system performs the step of generating a list identifying points on the boundary in the image for which there do not exist matching points on the boundary in the pattern.

15. In a system according to claim 14, the further improvement wherein the machine vision system performs the step of generating a list identifying points on the boundary in the pattern for which there do not exist matching points on the boundary in the image.

16. In a system according to claim 13, the further improvement wherein step (D) includes determining any of

(i) a distance relationship,

(ii) a direction relationship,

(iii) a contrast relationship,

between at least a selected point on the boundary in the image and the matching point on the boundary in the pattern.

17. In a system according to claim 16, the further improvement wherein step (E) includes generating the list so as to include any of the distance relationship, direction relationship, and contrast relationship between the matching points.

18. In a system according to claim 17, the further improvement wherein step (C) includes determining a distance between a point on the boundary in the image and a point on the boundary in the pattern.

19. In a system according to claim 18, the further improvement wherein step (C) includes identifying as corresponding a point on the boundary in the image that lies within a selected distance of a point on the boundary in the pattern.

20. In a machine vision system, the improvement for comparing a pattern and an image comprising performing the steps of:

A. finding points on a boundary in the image,

B. for each point on the boundary in the image, determining whether there exists a matching point on a boundary in the pattern,

C. generating a list identifying the points on the boundary in the image for which there exist matching points on the boundary in the pattern,

D. generating a list identifying points on the boundary in the image for which there do not exist matching points on the boundary in the pattern, and

E. generating a list identifying points on the boundary in the pattern for which there do not exist matching points on the boundary in the image.

21. In a system according to claim 20, the further improvement wherein step (C) includes determining, for each point on the boundary in the image for which there exists a matching point on the boundary in the pattern, any of a qualitative and a quantitative relationship between those matching points.

22. In a system according to claim 21, the further improvement wherein step (C) includes generating a list identifying the points on the boundary in the image for which there exist matching points on the boundary in the pattern and identifying any of the qualitative and quantitative relationships between those matching points.

23. In a system according to claim 22, the further improvement wherein step (C) includes determining any of

(i) a distance relationship,

(ii) a direction relationship,

(iii) a contrast relationship,

between at least a selected point on the boundary in the image and the matching point on the boundary in the pattern, and wherein step (C) further includes generating the list so as to include any of the distance relationship, direction relationship, and contrast relationship between the matching points.

24. In a system according to claim 23, the further improvement wherein step (C) includes identifying as corresponding a point on the boundary in the image that lies within a selected distance of a point on the boundary in the pattern.

25. In a machine vision method for comparing a pattern and an image, the improvement comprising:

A. identifying a boundary in the image and performing connectivity analysis to identify points on that boundary,

B. identifying a boundary in the pattern and performing connectivity analysis to identify points on that boundary,

C. for each point on the boundary in the image, determining whether there exists a matching point on the boundary in the pattern,

D. for each point on the boundary in the image for which there exists a matching point on the boundary in the pattern, determining any of a qualitative and a quantitative relationship between those matching points.

26. In a method according to claim 25, the further improvement comprising identifying points on the boundary in the image for which there do not exist matching points on the boundary in the pattern, and identifying points on the boundary in the pattern for which there do not exist matching points on the boundary in the image.