System and method for validating graphical components of images by synthesis

• US 20060110044A1
• 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: Reissman, Pierre-Jean
• Granted Patent: US 7,620,248 B2
• Time in Patent Office: Days
• US Class Current: 382/203
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06V 10/426 Graphical representations
• CPC Class Codes: G06V 10/945 User interactive design; Environments; Toolboxes
• CPC Class Codes: G06V 30/1983 Syntactic or structural pattern recognition, e.g. symbolic string recognition

Abstract

A system and method for improved validation of images is provided. Validation of any target image may be performed by creating a model of graphical components of a source image or a reference model and comparing the model of graphical components of the source image or reference model with a model of graphical components of the target image in order to detect differences between the graphical components. In one embodiment, a framework may be provided with an analysis engine for building a model of graphical components of a source image to be compared with a model of graphical components of a target image. In another embodiment, a framework may be provided with a synthesis engine for building a model of a synthesized graphical component to be compared with a model of graphical components of a target image.

Claims

1. A computer system for validating graphical components of images, comprising:

an image validation engine for validating a graphical component from a target image using a synthesized graphical component;

a synthesis engine operably coupled to the image validation engine for modeling the synthesized graphical component and for modeling the graphical component from the target image; and

an image comparator operably coupled to the image validation engine for comparing the synthesized graphical component with the graphical component from the target image.

2. The system of claim 1 further comprising a media library operably coupled to the image validation engine for capturing events in the system.

3. The system of claim 1 further comprising a user interface operably coupled to the image validation engine for exposing model designers and analysis tools.

4. The system of claim 1 further comprising a loader operably coupled to the image validation engine for providing components that may each include information for a specific test.

5. The system of claim 1 wherein the image comparator for comparing the synthesized graphical component with the graphical component from the target image comprises an image comparator for comparing a model of the synthesized graphical component with a model of the graphical component from the target image.

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

7. A method for validating graphical components of images in a computer system, comprising:

creating a model of a synthesized graphical component;

comparing the model of the synthesized graphical component with a model of a graphical component from a target image to detect differences between the graphical components; and

outputting results from the comparison of the models of the graphical components.

8. The method of claim 7 wherein creating the model of the synthesized graphical component comprises creating the synthesized graphical component using a design tool that may provide glyphs of graphical components.

9. The method of claim 7 further comprising creating the model of the graphical component from the target image.

10. The method of claim 9 wherein creating the model of the graphical component from the target image comprises modeling features in the target image

11. The method of claim 7 further comprising preprocessing the target image.

12. The method of claim 11 wherein preprocessing the target image comprises filtering the target image.

13. The method of claim 12 wherein filtering the target image comprises suppressing high frequencies in the image.

14. The method of claim 12 wherein filtering the target image comprises enhancing low frequencies in the image.

15. The method of claim 11 wherein preprocessing the target image comprises performing a geometrical transform on the image.

16. The method of claim 15 wherein performing a geometrical transform comprises performing a 2D affine transform.

17. The method of claim 10 wherein modeling features in the target image comprises finding a graphical component in the target image.

18. The method of claim 17 wherein finding a graphical component in the target image comprises identifying a shape in the target image by flood-filling adjacent pixels that are similar to a selected seed.

19. The method of claim 18 wherein flood-filling adjacent pixels that are similar to a selected seed comprises selecting a pixel in the image as the seed for flood-filling adjacent pixels similar to the seed.

20. The method of claim 18 further comprising computing feature matrices on the shape.

21. The method of claim 20 further comprising storing the results of computing the feature matrices on the shape in the model of the graphical component.

22. The method of claim 18 further comprising computing feature matrices on the color function.

23. The method of claim 22 further comprising storing the results of computing the feature matrices on the color function in the model of the graphical component.

24. The method of claim 18 further comprising tagging a feature modeled in the target image.

25. The method of claim 9 wherein creating a model of the graphical component from the target image comprises creating a tree with one or more child nodes, each node aggregating primitives detected within the source image.

26. The method of claim 7 wherein comparing the model of the synthesized graphical component with the model of the graphical component from the target image to detect differences between the graphical components comprises setting an adjustable tolerance level for comparing the graphical components.

27. The method of claim 26 wherein setting an adjustable tolerance level for comparing the graphical components comprises selecting one of a set of predefined tolerance levels.

28. The method of claim 27 wherein selecting one of a set of predefined tolerance levels comprises selecting one of a set of predefined tolerance curves.

29. The method of claim 7 wherein comparing the model of the synthesized graphical component with a model of a graphical component from a target image to detect differences between the graphical components comprises comparing pixels of the synthesized graphical component with corresponding pixels of the graphical component from the target image to detect differences between the pixels compared.

30. The method of claim 29 wherein comparing pixels of the synthesized graphical component with corresponding pixels of the graphical component from the target 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.

31. The method of claim 29 wherein comparing pixels of the synthesized graphical component with corresponding pixels of the graphical component from the target image to detect differences between the pixels compared comprises recording the result of the differences between pixels.

32. The method of claim 31 wherein recording the result of the differences between pixels comprises recording the result of the differences between pixels in a histogram.

33. A computer-readable medium having computer-executable instructions for performing the method of claim 7.

34. A method for validating images in a computer system, comprising:

creating a model of a synthesized graphical component;

creating a model of a target image;

comparing the model of the synthesized graphical component with the model of the target image to detect the presence of the synthesized graphical component within the target image; and

outputting results from the comparison of the models.

35. The method of claim 34 further comprising modeling features in the target image.

36. The method of claim 34 wherein creating the model of the synthesized graphical component comprises creating a tree with one or more child nodes, each node aggregating primitives detected within the synthesized graphical component.

37. The method of claim 34 wherein creating the model of the target image comprises creating a tree with one or more child nodes, each node aggregating primitives detected within the target image.

38. The method of claim 34 wherein comparing the model of the synthesized graphical component with the model of the target image to detect the presence of the synthesized graphical component within the target image comprises setting an adjustable tolerance level for comparing the models.

39. The method of claim 34 wherein comparing the model of the synthesized graphical component with the model of the target image to detect the presence of the synthesized graphical component within the target image comprises comparing pixels of the synthesized graphical component with corresponding pixels of the target image to detect differences between the pixels compared.

40. The method of claim 39 wherein comparing pixels of the synthesized graphical component with corresponding pixels of the target image to detect differences between the pixels compared comprises comparing the differences detected with an adjustable tolerance level set for comparing the synthesized graphical component with the target image.