Multilevel chain-and-tree model for image-based decisions

• US 20030179936A1
• Filed: 03/22/2002
• Published: 09/25/2003
• Est. Priority Date: 03/22/2002
• Status: Active Grant

• Current Assignee: Nikon Corporation
• Original Assignee: Chi-Chou Huang, Shih-Jong J. Lee
• Inventors: Huang, Chi-Chou, Lee, Shih-Jong J.
• Granted Patent: US 7,116,825 B2
• Time in Patent Office: Days
• US Class Current: 382/226
• CPC Class Codes: G06F 18/24323 Tree-organised classifiers
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume
• CPC Class Codes: G06T 7/66 of image moments or centre of gravity

Abstract

A multilevel Chain-And-Tree model provides a framework for an image based decision system. The decision system enables separation of effects of defects within one component from other components within a common subject. The framework provides for linking of structure constraints of components of a common subject and for checking and resolving their consistency. The framework allows discrimination between subtle image changes and natural variations of the subject. The framework for standard data representation facilitates production process control.

Claims

1. An image-based decision method using a multilevel Chain-And-Tree model comprises the following steps:

(a) Input at least one reference CAT model basis selected from the set consisting of inspection specification, learning image, and application knowledge;

(b) Create a reference CAT model using at least one reference CAT model basis;

(c) Input a new image;

(d) Create a result CAT model;

(e) Compare the reference CAT model and result CAT model to output a measurement result.

2. The method of claim 1 further comprises a step to determine at least one pass/fail status.

3. The method of claim 1 wherein the reference CAT model consists of the basic structure and attribute values of an ideal subject and its tolerance ranges.

4. The method of claim 1 wherein the result CAT model represents the measurement results of a new image.

5. The method of claim 1 wherein the CAT model contains at least one CAT chain.

6. The method of claim 1 wherein the CAT model contains at least one CAT tree.

7. The method of claim 1 wherein the CAT model contains at least one CAT node.

8. The method of claim 7 wherein the CAT node contains CAT component type specification, CAT component feature specification and CAT component relation specification.

9. The method of claim 5 wherein the CAT chain contains at least one chain root node and at least one chain node.

10. The method of claim 6 wherein the CAT tree contains at least one tree root node and at least one tree node.

11. An image-based decision method using a multilevel Chain-And-Tree model comprises the following steps:

(a) Input inspection specification;

(b) Input at least one learning image;

(c) Create a reference CAT model using the inputs;

(d) Create a processing CAT model using the inputs and the reference CAT model;

(e) Input a new image;

(f) Create a result CAT model using the processing CAT model and the new image;

(g) Compare the reference CAT model and result CAT model to output at least one result.

12. The method of claim 11 further comprises a step to input application knowledge.

13. The method of claim 11 wherein the result is a measurement result of the new image.

14. The method of claim 11 wherein the result is a pass/fail result of the new image.

15. The method of claim 11 wherein the reference CAT model consists of the basic structure and attribute values of an ideal subject.

16. The method of claim 15 wherein the attribute values of the ideal subject include its tolerance ranges.

17. The method of claim 11 wherein the processing CAT model includes detection methods.

18. The method of claim 11 wherein the result CAT model represents the measurement results from a new image.

19. The method of claim 11 wherein the CAT model contains at least one CAT chain.

20. The method of claim 11 wherein the CAT model contains at least one CAT tree.

21. The method of claim 11 wherein the CAT model contains at least one CAT node.

22. The method of claim 21 wherein the CAT node contains CAT component type specification, CAT component feature specification and CAT component relation specification.

23. The method of claim 19 wherein the CAT chain contains at least one chain root node and one or more chain nodes.

24. The method of claim 20 wherein the CAT tree contains at least one tree root node plus one or more tree nodes.

25. An image-based decision method using a common structure comprises the following steps:

(h) Create a reference model having a common structure;

(i) Create a processing model having said common structure;

(j) Input a new image;

(k) Create a result model having said common structure using the processing model and the new image;

(l) Compare the reference model and result model to output a result pass/fail status.

26. The method of claim 25 wherein the result includes at least one measurement result.

27. The method of claim 25 wherein the result includes at least one pass/fail status.

28. The method of claim 25 wherein said common structure is a CAT model.

29. The method of claim 25 wherein said common structure is a CAD model.