Constraint generation for use in image segregation

• US 20100142805A1
• Filed: 12/05/2008
• Published: 06/10/2010
• Est. Priority Date: 12/05/2008
• Status: Active Grant

• Current Assignee: Innovation Asset Collective
• Original Assignee: Tandent Vision Science, Inc.
• Inventors: Smith, Casey Arthur, Tolliver, David Allen, Bushell, Steven Joseph, Friedhoff, Richard Mark, Stein, Andrew Neil, Bagnell, James Andrew, Maxwell, Bruce Allen, Dana, Kristin Jean, Kwak, Iljung Samuel, Leonardus Nabbe, Bartholomeus Christianus, Diebel, Milan, Rodgers, Timothy King JR.
• Granted Patent: US 8,139,850 B2
• Time in Patent Office: Days
• US Class Current: 382/164
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06V 10/273 removing elements interfering with the pattern to be recognised
• CPC Class Codes: G06V 10/443 by matching or filtering
• CPC Class Codes: G06V 10/457 by analysing connectivity, e.g. edge linking, connected component analysis or slices

Abstract

In an exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image, organizing spatio-spectral information for the image in a matrix equation expressed by: [A][x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the spatio-spectral information, [b] expresses recorded information for the image, and [x] expresses an unknown material/illumination component of the image, and utilizing the matrix equation in an image segregation operation.

Claims

1. An automated, computerized method for processing an image, comprising the steps of:

providing an image;

organizing spatio-spectral information for the image in a matrix equation expressed by;

[A] [x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the spatio-spectral information, [b] expresses recorded information for the image, and [x] expresses an unknown material/illumination component of the image; and

utilizing the matrix equation in an image segregation operation.

2. The method of claim 1 wherein the spatio-spectral information includes a token.

3. The method of claim 1 wherein the spatio-spectral information includes a log chromaticity representation.

4. The method of claim 1 wherein the spatio-spectral information includes an X-junction

5. The method of claim 1 wherein the spatio-spectral information includes a BIDR model representation.

6. The method of claim 1 wherein the spatio-spectral information includes a boundary representation.

7. The method of claim 1 wherein the spatio-spectral information includes a texton histogram based pixel representation.

8. The method of claim 1 wherein the constraining relationship comprises one of an absolute material color constraint, a same material constraint and a relative reflectance constraint.

9. An automated, computerized method for processing an image, comprising the steps of:

providing an image;

generating spatio-spectral information for the image;

defining a constraint as a function of the spatio-spectral information; and

utilizing the constraint in an image segregation operation.

10. The method of claim 9 wherein the spatio-spectral information includes a token.

11. The method of claim 9 wherein the spatio-spectral information includes a log chromaticity representation.

12. The method of claim 9 wherein the spatio-spectral information includes an X-junction

13. The method of claim 9 wherein the spatio-spectral information includes a BIDR model representation.

14. The method of claim 9 wherein the spatio-spectral information includes a boundary representation.

15. The method of claim 9 wherein the spatio-spectral information includes a texton histogram based pixel representation.

16. The method of claim 9 wherein the constraint comprises one of an absolute material color constraint, a same material constraint and a relative reflectance constraint.

17. An automated, computerized method for processing an image, comprising the steps of:

providing an image;

organizing spatio-spectral operators as a function of a BIDR model representation of the image; and

utilizing a result of the organizing step to identify material and illumination aspects of the image for image segregation.

18. The method of claim 17 wherein the step of organizing spatio-spectral operators as a function of a BIDR model representation of the image is carried out by constraining tokens representing regions of robust similar color to a BIDR model representation of the image.

19. The method of claim 18 wherein the step of constraining tokens representing regions of robust similar color to a BIDR model representation of the image is carried out by constraining the tokens representing regions of robust similar color relative to a linear token.

20. An automated, computerized method for processing an image, comprising the steps of:

providing an image;

organizing spatio-spectral operators as a function of tokens representing discrete materials depicted in the image and tokens representing regions of robust similar color; and

utilizing a result of the organizing step to identify material and illumination aspects of the image for image segregation.

21. The method of claim 20 wherein the step of organizing spatio-spectral operators as a function of tokens representing discrete materials depicted in the image and tokens representing regions of robust similar color is carried out by constraining the tokens to a constraint selected from the group consisting of an absolute material color constraint, a same material constraint and a relative reflectance constraint.

22. An automated, computerized method for processing an image, comprising the steps of:

providing an image file depicting an image, in a computer memory;

identifying information in the image file relevant to a logical deduction regarding material and illumination aspects of an image;

defining a constraint as a function of the information; and

utilizing the constraint in an image segregation operation.

23. An automated, computerized method for processing an image, comprising the steps of:

providing an image file depicting an image, in a computer memory;

organizing information for the image file relevant to a logical deduction regarding material and illumination aspects of an image, in a matrix equation expressed by;

[A] [x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the information relevant to a logical deduction regarding material and illumination aspects of an image, [b] expresses information obtained form the image file, in the computer memory, and [x] expresses an unknown material/illumination component of the image; and

utilizing the matrix equation in an image segregation operation.

24. The method of claim 23 wherein the information for the image file relevant to a logical deduction regarding material and illumination aspects of an image is selected from information relevant to spatio-spectral aspects of an image.

25. A computer system which comprises:

a CPU; and

a memory storing an image file defining an image;

the CPU being arranged and configured to execute a routine to identify information in the image file relevant to a logical deduction regarding material and illumination aspects of an image, define a constraint as a function of the information and utilize the constraint in an image segregation operation.

26. A computer system which comprises:

a CPU; and

a memory storing an image file defining an image;

the CPU being arranged and configured to execute a routine to organize information for the image file relevant to a logical deduction regarding material and illumination aspects of an image, in a matrix equation expressed by;

[A] [x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the information relevant to a logical deduction regarding material and illumination aspects of an image, [b] expresses information obtained form the image file, in the computer memory, and [x] expresses an unknown material/illumination component of the image and utilize the matrix equation in an image segregation operation.

27. A computer program product, disposed on a computer readable media, the product including computer executable process steps operable to control a computer to:

provide an image file depicting an image, in a computer memory;

identify information in the image file relevant to a logical deduction regarding material and illumination aspects of an image;

define a constraint as a function of the information; and

utilize the constraint in an image segregation operation.

28. The computer program product of claim 27 wherein the information in the image file relevant to a logical deduction regarding material and illumination aspects of an image is selected from information relevant to spatio-spectral aspects of an image.

29. A computer program product, disposed on a computer readable media, the product including computer executable process steps operable to control a computer to:

provide an image file depicting an image, in a computer memory;

organize information for the image file relevant to a logical deduction regarding material and illumination aspects of an image, in a matrix equation expressed by;

[A] [x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the information relevant to a logical deduction regarding material and illumination aspects of an image, [b] expresses information obtained form the image file, in the computer memory, and [x] expresses an unknown material/illumination component of the image; and

utilize the matrix equation in an image segregation operation.

30. The computer program product of claim 29 wherein the information for the image file relevant to a logical deduction regarding material and illumination aspects of an image is selected from information relevant to spatio-spectral aspects of an image.