Loose gray-scale template matching for image processing of anti-aliased lines

• US 6,944,341 B2
• Filed: 01/24/2001
• Issued: 09/13/2005
• Est. Priority Date: 05/01/2000
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Loce, Robert P., Cuciurean-Zapan, Clara
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): STREGE, JOHN B
• Application Number:
  US09/768,161
• Publication Number:
  US 20010038712A1
• Time in Patent Office: 1,693 Days
• Field of Search: 382/190, 382/209, 382/181, 382/299, 382/282, 382/269, 382/266, 382/264, 382/218, 382/217, 382/278, 345611-616
• US Class Current: 382/209
• CPC Class Codes: H04N 1/409 Edge or detail enhancement; Noise or error suppression

Abstract

An anti-aliased, or gray-edged, image is characterized by comparing the image to a number of loose-templates having a plurality of elements and at least one element having a range greater than zero. As families of loose-templates are compared to the anti-aliased input image, one or more sets of patterns, or features, are recognized and extracted to produce various screens of features that generally describe the anti-aliased input image. An arbitration technique is then performed on the sets of features to produce feature vectors which, in turn, can be used to control line-widths within the anti-aliased input image.

Claims

1. A method for processing anti-aliased images comprising:

comparing at least one image portion of an anti-aliased input image against one or more loose-templates to produce a comparison image; and

processing the comparison image to determine whether a match condition is satisfied.

2. The method of claim 1, wherein the step of processing controls at least one or more line-widths of the comparison image.

3. The method of claim 1, wherein the step of comparing the anti-aliased image includes:

extracting the at least one image portion from the anti-aliased input image; and

performing a pattern matching operation between at least one loose-template and the at least one image portion to produce a screen containing at least one or more features.

4. The method of claim 3, wherein the step of comparing further includes arbitrating between at least two or more features in the screen.

8. The method of claim 1, wherein the step of comparing further includes producing one or more feature vectors.

9. The method of claim 1, wherein the comparison image is an anti-aliased image.

10. The method of claim 1, wherein the step of comparing includes reducing a resolution of at least a portion of the anti-aliased input image.

11. The method of claim 10, further comprising comparing the anti-aliased image portion to at least one template.

12. The method of claim 2, wherein controlling the line-width of at least one of the one or more lines of the comparison image includes controlling a growth of the at least one line-width.

13. The method of claim 12, wherein controlling the line-widths uses at least a look-up table.

26. The method of claim 1, wherein the step of comparing includes:

determining a characteristic relation between the at least one portion of the comparison image and the template to produce a characteristic determination;

comparing the characteristic determination against a template threshold; and

determining whether the characteristic determination satisfies a template comparison condition based on comparing against the template threshold.

27. The method of claim 26, wherein at least one of the one or more loose-templates contains a plurality of template elements, and the template threshold contains a uniform threshold value for the plurality of template elements.

28. The method of claim 26, wherein at least one of the one or more loose-templates contains a plurality of template elements, and the template threshold contains a corresponding threshold values for each template element of the plurality of template elements.

32. The method of claim 26, wherein the template includes a plurality of template elements, each template element having a target value and a span.

5. A method for processing anti-aliased images, comprising:

characterizing an anti-aliased input image using one or more loose-templates; and

processing the characterized image to affect a second image, wherein the step of characterizing the anti-aliased image includes;

extracting one or more image portions from the anti-aliased input image; and

performing a pattern matching operation between at least one loose-template and at least one image portion to produce a screen containing at least one or more features, wherein the step of characterizing further includes arbitrating between at least two or more features in the screen, and the step of arbitrating effectively eliminates at least one feature.

6. A method for processing anti-aliased images, comprising:

characterizing an anti-aliased input image using one or more loose-templates; and

processing the characterized image to affect a second image, wherein the step of characterizing the anti-aliased image includes;

extracting one or more image portions from the anti-aliased input image; and

performing a pattern matching operation between at least one loose-template and at least one image portion to produce a screen containing at least one or more features, wherein the step of characterizing further includes arbitrating between at least two or more features in the screen, and the step of arbitrating produces a new feature.

7. A method for processing anti-aliased images, comprising:

characterizing an anti-aliased input image using one or more loose-templates; and

processing the characterized image to affect a second image, wherein the step of characterizing the anti-aliased image includes;

extracting one or more image portions from the anti-aliased input image; and

performing a pattern matching operation between at least one loose-template and at least one image portion to produce a screen containing at least one or more features, wherein the step of characterizing further includes arbitrating between at least two or more features in the screen, and the step of characterizing further includes arbitrating between at least two or more screens.

14. An apparatus for processing images comprising:

at least one loose-template; and

a control device that produces a comparison image based on comparing the at least one loose-template against an anti-aliased image to determine whether a match condition is satisfied.

15. The apparatus of claim 14, wherein the control device controls at least one or more line-widths of the comparison image.

16. The apparatus of claim 14, further comprising:

a windowing device that extracts one or more image portions from the anti-aliased image; and

a pattern matching device that performs at least one pattern matching operation between the at least one loose-template and at least one anti-aliased image portion to produce a screen containing at least one or more features.

17. The apparatus of claim 16, further comprising an arbitration device that arbitrates between at least two or more features in the screen.

21. The apparatus of claim 14, wherein the control device produces one or more feature vectors based on the anti-aliased input image and one or more loose-templates.

22. The apparatus of claim 14, wherein the comparison image is a second anti-aliased image.

23. The apparatus of claim 14, wherein the windowing device reduces a resolution of at least a portion of the anti-aliased image.

29. The apparatus of claim 14, wherein the control device includes:

a relating device that determines a characteristic relation between the at least one portion of the comparison image and the template to produce a characteristic determination;

a comparing device that compares the characteristic determination against a template threshold; and

a satisfying device that determines whether the characteristic determination satisfies a template comparison condition based on comparing against the template threshold.

30. The apparatus of claim 29, wherein at least one of the one or more loose-templates contains a plurality of template elements, and the template threshold contains a uniform threshold value for the plurality of template elements.

31. The apparatus of claim 29, wherein at least one of the one or more loose-templates contains a plurality of template elements, and the template threshold contains a corresponding threshold values for each template element of the plurality of template elements.

33. The apparatus of claim 29, wherein the template includes a plurality of template elements, each template element having a target value and a span.

18. An apparatus for processing images, comprising:

one or more loose-templates;

a control device that affects a second image based on the one or more loose-templates and an anti-aliased image;

a windowing device that extracts one or more image portions from the anti-aliased image;

a pattern matching device that performs at least one pattern matching operation between at least one loose-template and at least one anti-aliased image portion to produce a screen containing at least one or more features; and

an arbitration device that arbitrates between at least two or more features in the screen, wherein the arbitration device effectively eliminates at least one feature.

19. An apparatus for processing images, comprising:

one or more loose-templates;

a control device that affects a second image based on the one or more loose-templates and an anti-aliased image;

a windowing device that extracts one or more image portions from the anti-aliased image;

a pattern matching device that performs at least one pattern matching operation between at least one loose-template and at least one anti-aliased image portion to produce a screen containing at least one or more features; and

an arbitration device that arbitrates between at least two or more features in the screen, wherein arbitration device produces a new feature.

20. An apparatus for processing images, comprising:

one or more loose-templates;

a control device that affects a second image based on the one or more loose-templates and an anti-aliased image;

a windowing device that extracts one or more image portions from the anti-aliased image;

a pattern matching device that performs at least one pattern matching operation between at least one loose-template and at least one anti-aliased image portion to produce a screen containing at least one or more features; and

an arbitration device that arbitrates between at least two or more features in the screen, wherein the arbitration device further arbitrates between at least two or more screens.

24. A method for processing anti-aliased images comprising:

comparing at least one image portion of an anti-aliased input image against one or more loose-templates to produce a comparison image, each loose-template having a plurality of image elements, wherein at least one of the image elements has a range greater than one; and

processing the comparison image to determine whether a match condition is satisfied.

25. An apparatus for processing images comprising:

one or more loose-templates each having a plurality of image elements, wherein at least one image element has a range greater than one; and

a control device that produces a comparison image based on comparing the at least one loose-template against an anti-aliased image to determine whether a match condition is satisfied.