Fuzzy image comparator

• US 20060110047A1
• Filed: 11/19/2004
• Published: 05/25/2006
• Est. Priority Date: 11/19/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Cauchy, Marc, Reissman, Pierre-Jean
• Granted Patent: US 7,477,785 B2
• Time in Patent Office: Days
• US Class Current: 382/218
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching

Abstract

A system and method for improved image comparison is provided. An adjustable tolerance level may be set for comparing the images, and filtering may be applied to the images, for example, to suppress high frequencies in the images or to enhance low frequencies in the images. Furthermore, a geometrical transform, such as a 2D affine transform, may be applied to one of the images. The pixels of one of the images may be compared with corresponding pixels of another image to detect differences between the pixels compared. Then the outcome of comparing the pixels of the images may be determined by comparing the differences detected with the tolerance level set. The tolerance may be set by selecting one of a set of predefined tolerance levels, each of which may represent a different degree of tolerance to be used in comparison of the images.

Claims

1. A computer system for comparing images, comprising:

a pixel comparator for comparing pixels of one image with corresponding pixels of another image to detect differences between the pixels compared;

a results manager operably coupled to the pixel comparator for determining the outcome of comparing the pixels of the images by comparing the differences detected with a set tolerance level; and

a tolerance adjuster operably coupled to the results manager for setting an adjustable tolerance level.

2. The system of claim 1 further comprising a filtering engine operably coupled to the pixel comparator for filtering the images.

3. The system of claim 1 further comprising a transform engine operably coupled to the pixel comparator for performing a 2D affine transform on one of the images.

4. The system of claim 1 further comprising a user interface operably coupled to the tolerance adjuster, the user interface including at least one application programming interface for setting the tolerance level.

5. The system of claim 1 wherein the images comprise a sequence of graphical user interface screens.

6. The system of claim 1 wherein one of the images comprises a visual primitive used to build a graphical user interface screen.

7. The system of claim 1 wherein the tolerance level comprises a set of mathematical representations.

8. A computer-readable medium having computer-executable components comprising the system of claim 1.

9. A method for comparing images in a computer system, comprising:

preprocessing images to be compared, including setting an adjustable tolerance level for comparing images;

comparing pixels of one of the images with corresponding pixels of another image to detect differences between the pixels compared;

determining the outcome of comparing the pixels of the images by comparing the differences detected with the tolerance level set; and

outputting results of the determination.

10. The method of claim 9 wherein preprocessing the images to be compared comprises filtering the images.

11. The method of claim 10 wherein filtering the images comprises suppressing high frequencies in the images.

12. The method of claim 10 wherein filtering the images comprises enhancing low frequencies in the images.

13. The method of claim 9 wherein preprocessing the images to be compared comprises performing a geometrical transform on one of the images.

14. The method of claim 13 wherein performing a geometrical transform comprises performing a 2D affine transform.

15. The method of claim 9 wherein setting an adjustable tolerance level for comparing images comprises selecting one of a set of predefined tolerance levels.

16. The method of claim 15 wherein selecting one of a set of predefined tolerance levels comprises selecting one of a set of predefined tolerance curves.

17. The method of claim 9 wherein setting an adjustable tolerance level for comparing images comprises automatically selecting one of a set of predefined tolerance levels based upon an image type of one of the images.

18. The method of claim 15 wherein selecting one of a set of predefined tolerance levels comprises initializing the adjustable tolerance level to a default tolerance level.

19. The method of claim 9 wherein comparing pixels of one of the images with corresponding pixels of another image to detect differences between the pixels compared comprises measure the distance between the colors of the pixels as the sum of the absolute difference between the R, G, B and alpha channels.

20. The method of claim 9 wherein comparing pixels of one of the images with corresponding pixels of another image to detect differences between the pixels compared comprises recording the result of the differences between pixels.

21. The method of claim 20 wherein recording the result of the differences between pixels comprises recording the result of the differences between pixels in a histogram.

22. A computer-readable medium having computer-executable instructions for performing the method of claim 9.

23. A computer-readable medium having computer-executable instructions, comprising:

setting an adjustable tolerance level for comparing images;

comparing pixels of one of the images with corresponding pixels of another image to detect differences between the pixels compared;

determining the outcome of comparing the pixels of the images by comparing the differences detected with the tolerance level set; and

outputting the results of the determination.

24. The computer-readable medium of claim 23 further comprising filtering the images.

25. The computer-readable medium of claim 24 wherein filtering the images comprises suppressing high frequencies in the images.

26. The computer-readable medium of claim 24 wherein filtering the images comprises enhancing low frequencies in the images.

27. The computer-readable medium of claim 23 further comprising performing a geometrical transform on one of the images.

28. The computer-readable medium of claim 27 wherein performing a geometrical transform comprises performing a 2D affine transform.

29. The computer-readable medium of claim 23 wherein setting an adjustable tolerance level for comparing images comprises selecting one of a set of predefined tolerance levels.

30. The computer-readable medium of claim 29 wherein selecting one of a set of predefined tolerance levels comprises selecting one of a set of predefined tolerance curves.

31. The computer-readable medium of claim 23 wherein setting an adjustable tolerance level for comparing images comprises automatically selecting one of a set of predefined tolerance levels based upon an image type of one of the images.

32. The computer-readable medium of claim 29 wherein selecting one of a set of predefined tolerance levels comprises initializing the adjustable tolerance level to a default tolerance level.

33. The computer-readable medium of claim 23 wherein comparing pixels of one of the images with corresponding pixels of another image to detect differences between the pixels compared comprises measure the distance between the colors of the pixels as the sum of the absolute difference between the R, G, B and alpha channels.

34. The computer-readable medium of claim 23 wherein comparing pixels of one of the images with corresponding pixels of another image to detect differences between the pixels compared comprises recording the result of the differences between pixels.

35. The computer-readable medium of claim 34 wherein recording the result of the differences between pixels comprises recording the result of the differences between pixels in a histogram.

36. The computer-readable medium of claim 35 wherein determining the outcome of comparing the pixels of the images by comparing the differences detected with the tolerance level set comprises determining the outcome of comparing the pixels of the images by comparing the results recorded in the histogram with the tolerance level set.

37. A computer system for comparing images, comprising:

means for preprocessing images to be compared, including setting an adjustable tolerance level for comparing images;

means for comparing pixels of one of the images with corresponding pixels of another image to detect differences between the pixels compared;

means for determining the outcome of comparing the pixels of the images by comparing the differences detected with the tolerance level set; and

means for outputting results of the determination.

38. The system of claim 37 wherein the means for preprocessing the images to be compared comprises means for filtering the images.

39. The system of claim 37 wherein the means for preprocessing the images to be compared comprises means for performing a geometrical transform on one of the images.

40. The system of claim 37 wherein the means for setting an adjustable tolerance level for comparing images comprises means for selecting one of a set of predefined tolerance levels.