Granted Patent B2

US 7,840,074 · App. 10/886,937 · Granted Nov 23, 2010

Abstract

Claims (62)

1. A method of identifying a boundary in an image, the method comprising:

identifying a search region containing pixels on both sides of the boundary in the image;

determining, using a processing unit, a plurality of color regions corresponding to a plurality of pixel classifications, wherein an error function represents a probability that each of the pixels within the search region belongs to one of the plurality of pixel classifications;

constructing, using the processing unit, an edge map by detecting edges of one or more objects in the image; and

creating, using the processing unit, an active contour based on minimizing energy of the active contour using the error function and the edge map.

2. The method of claim 1 , wherein the search region is associated with an edge of an object in the image.

3. The method of claim 1 , further comprising:

creating a plurality of active contours; and

identifying a best active contour from the plurality of active contours.

4. The method of claim 1 , wherein the search region is symmetrically disposed about a straight line joining two points on a boundary of an object in the image.

5. The method of claim 1 , wherein the search region is in the shape of a rectangle.

6. The method of claim 1 , wherein the search region is in the shape of an ellipse.

7. The method of claim 1 , further comprising rotating the search region to create a one-dimensional active contour.

8. The method of claim 1 , wherein the search region is identified by two user supplied points.

9. The method of claim 1 , wherein the edge map is also constructed using an edge finding filter.

10. The method of claim 1 , wherein the active contour is further based on minimizing internal forces including one or more of stiffness and elasticity.

11. The method of claim 1 , wherein the impact of the error function and the edge map on minimizing energy of the active contour are weighted using empirical weighting coefficients.

12. The method of claim 1 , further comprising:

smoothing the active contour by averaging contour coordinates after minimizing energy of the active contour.

13. The method of claim 1 , further comprising:

classifying each of the pixels within the search region into one of the plurality of pixel classifications.

14. A method of identifying a boundary in an image, the method comprising:

identifying a search region containing pixels on both sides of the boundary in the image;

determining, using a processing unit, a plurality of color regions corresponding to a plurality of pixel classifications, wherein an error function represents a probability that each of the pixels within the search region belongs to one of the plurality of pixel classifications;

constructing, using the processing unit, an edge map by detecting edges of one or more objects in the image;

creating, using the processing unit, a plurality of active contours based on minimizing energy of each of the active contours using the error function and the edge map; and

identifying, using the processing unit, a best active contour from the plurality of active contours.

15. The method of claim 14 , wherein the best active contour most closely matches the boundary of the object in the image.

16. The method of claim 14 , wherein identifying a best active contour includes identifying an active contour having a lowest associated error function value.

17. The method of claim 14 , wherein the search region is symmetrically disposed about a straight line joining the at least two points on the boundary of the object in the image.

18. The method of claim 14 , further comprising rotating the search region to create a one-dimensional active contour.

19. One or more non-transitory computer-readable storage media having stored thereon a computer program that, when executed by one or more processors, causes the one or more processors to:

identify a search region containing pixels on both sides of a boundary in an image;

determine a plurality of color regions corresponding to a plurality of pixel classifications, wherein an error function represents a probability that each of the pixels within the search region belongs to one of the plurality of pixel classifications;

construct an edge map by detecting edges of one or more objects in the image; and

create an active contour based on minimizing energy of the active contour using the error function and the edge map.

20. The computer-readable storage media of claim 19 , further comprising determining at least one image gradient in the search region.

21. The computer-readable storage media of claim 19 , wherein the search region is identified by at least two points on a boundary of an object in the image.

22. The computer-readable storage media of claim 19 , wherein the search region is in the general shape of a rectangle.

23. An apparatus comprising:

a memory storing:

an image selection module to identify an image;

a search region selector coupled to the image selection module, the search region selector to identify a search region containing pixels on both sides of a boundary in the image;

an image gradient identification module coupled to the image selection module, the image gradient identification module to determine image gradients in the search region and construct an edge map by detecting edges of one or more objects in the image;

a color region identification module coupled to the image selection module, the color region identification module to determine a plurality of color regions corresponding to a plurality of pixel classifications, wherein an error function represents a probability that each of the pixels within the search region belongs to one of the plurality of pixel classifications; and

an active contour generation module coupled to the image gradient identification module and the color region identification module, the active contour generation module to generate at least one active contour based on minimizing energy of the at least one active contour using the error function and the edge map.

24. The apparatus of claim 23 , further comprising an active contour optimization module coupled to the active contour generation module, the active contour optimization module to identify a best active contour among the available active contours.

25. One or more non-tansitory computer-readable storage media having stored thereon a computer program that, when executed by one or more processors, causes the one or more processors to:

identify a search region containing pixels on both sides of a boundary in an image;

determine a plurality of color regions corresponding to a plurality of pixel classifications, wherein an error function represents a probability that each of the pixels within the search region belongs to one of the plurality of pixel classifications;

construct an edge map by detecting edges of one or more objects in the image;

create a plurality of active contours based on minimizing energy of the active contour using the error function and the edge map; and

identify a best active contour from the plurality of active contours.

26. The computer-readable storage media of claim 25 , wherein the best active contour most closely matches the boundary of the object in the image.

27. The computer-readable storage media of claim 25 , wherein the search region is in the general shape of a rectangle.

28. A method of identifying a boundary in an image, the method comprising:

identifying a search region containing pixels on both sides of the boundary in the image;

determining, using a processing unit, a plurality of color regions corresponding to a plurality of pixel classifications, wherein an error function represents a probability that each of the pixels within the search region belongs to one of the plurality of pixel classifications;

constructing, using the processing unit, an edge map using image gradients; and

creating, using the processing unit, an active contour based on minimizing energy of the active contour using the error function and the edge map.

29. The method of claim 28 , wherein the image gradients are associated with at least a portion of an edge of an object in the image.

30. The method of claim 28 , wherein determining image gradients includes detecting image gradients at a plurality of different scales.

Assignments (20)