System and method for scanned image bleedthrough processing

• US 20040008884A1
• Filed: 07/12/2002
• Published: 01/15/2004
• Est. Priority Date: 07/12/2002
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Simske, Steven John, Burns, Roland John
• Granted Patent: US 7,209,599 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: H04N 1/4095 Correction of errors due to scanning a two-sided document, i.e. show-through correction

Abstract

Disclosed are systems and methods for identifying bleedthrough in an image in which a reference tone point of a first image is determined, putative bleedthrough pixels in the first image are identified as a function of the reference tone point, the putative bleedthrough pixels are mapped into a putative bleedthrough representation of said first image, and the putative bleedthrough pixel mapping is analyzed to determine if bleedthrough is present in said first image. Also disclosed are systems and methods for removing bleedthrough from an image in which a document is scanned to provide an electronic first image and an electronic second image, a putative bleedthrough pixel mapping for the first image is generated, the putative bleedthrough pixel mapping is processed using information with respect to said second image, and pixels of the first image corresponding to putative bleedthrough pixels of said mapping are replaced.

Claims

1. A method for identifying bleedthrough in an image, said method comprising:

determining a reference tone point of a first image;

identifying putative bleedthrough pixels in said first image as a function of said reference tone point;

mapping said putative bleedthrough pixels into a putative bleedthrough representation of said first image; and

analyzing said putative bleedthrough pixel mapping to determine if bleedthrough is present in said first image.

2. The method of claim 1, wherein said identifying putative bleedthrough pixels comprises analyzing a histogram of pixel information to determine a bleedthrough pixel value relative to a value of said reference tone point.

3. The method of claim 1, wherein said reference tone point is a white point of said first image.

4. The method of claim 1, wherein said reference tone point is a black point of said first image.

5. The method of claim 1, wherein said analyzing said putative bleedthrough pixel mapping comprises determining if said putative bleedthrough pixels are clustered into regions larger than expected by a random distribution.

6. The method of claim 1, wherein said analyzing said putative bleedthrough pixel mapping comprises determining if said putative bleedthrough pixels comprise more than a predetermined percentage of the pixels of said first image.

7. The method of claim 6, wherein said predetermined percentage is 2.5%.

8. The method of claim 1, further comprising fattening regions of putative bleedthrough pixels in said mapping to thereby soften a visual impact associated with replacing pixels of said first image corresponding to said putative bleedthrough pixels.

9. The method of claim 1, further comprising, if said analyzing said putative bleedthrough pixel mapping indicates bleedthrough is present in said first image replacing pixels of said first image corresponding to putative bleedthrough pixels of said mapping using quasi-random replacement pixels.

10. The method of claim 9, wherein said quasi-random replacement comprises using a distribution of a first type of pixels of said first image with respect to the replaced pixels.

11. A method for processing bleedthrough in an image, said method comprising:

identifying putative bleedthrough pixels in a first image;

mapping said putative bleedthrough pixels into a putative bleedthrough representation of said first image; and

processing said putative bleedthrough pixel mapping to remove false positive bleedthrough pixels therefrom.

12. The method of claim 11, wherein said processing said putative bleedthrough pixel mapping comprises comparing information with respect to a second image to said putative bleedthrough pixel mapping and removing putative bleedthrough pixels from said mapping where there is no corresponding pixel in said second image.

13. The method of claim 12, further comprising, before said comparing said information with respect to said second image to said putative bleedthrough pixel mapping, scaling a resolution of one of said first and second images having a higher resolution down to a resolution of the other one of said first and second images.

14. The method of claim 12, wherein said comparing said information with respect to second image to said putative bleedthrough pixel mapping comprises alignment and skew adjusting said information with respect to said second image for said comparing with said putative bleedthrough pixel mapping.

15. The method of claim 11, wherein said processing said putative bleedthrough pixel mapping comprises deleting regions of putative bleedthrough pixels in said mapping smaller than a threshold value from said putative bleedthrough pixel mapping.

16. The method of claim 11, wherein said processing said putative bleedthrough pixel mapping comprises thinning regions of putative bleedthrough pixels in said mapping to thereby remove a portion of said regions.

17. The method of claim 11, further comprising fattening regions of putative bleedthrough pixels in said mapping to thereby soften a visual impact associated with replacing pixels of said first image corresponding to said putative bleedthrough pixels.

18. The method of claim 11, further comprising replacing pixels of said first image corresponding to putative bleedthrough pixels of said mapping using quasi-random replacement pixels.

19. The method of claim 18, wherein said quasi-random replacement comprises using a distribution of a first type of pixels of said first image with respect to the replaced pixels.

20. A method for removing bleedthrough from an image, said method comprising:

scanning a document to provide an electronic first image;

scanning said document to provide an electronic second image, wherein said first and second images are associated with juxtaposed sides of said document;

generating a putative bleedthrough pixel mapping for said first image;

processing said putative bleedthrough pixel mapping using information with respect to said second image; and

replacing pixels of said first image corresponding to putative bleedthrough pixels of said mapping.

21. The method of claim 20, wherein said scanning to provide said first image and said scanning to provide said second image are at different resolutions.

22. The method of claim 21, further comprising scaling a resolution of one of said first and second images having a higher resolution down to a resolution of the other one of said first and second images.

23. The method of claim 20, wherein said processing said putative bleedthrough pixel mapping removes false positive bleedthrough pixels therefrom.

24. The method of claim 20, wherein said processing said putative bleedthrough pixel mapping comprises comparing information with respect to said second image to said putative bleedthrough pixel mapping and removing putative bleedthrough pixels from said mapping where there is no corresponding pixel in said second image.

25. The method of claim 24, wherein said comparing said information with respect to said second image to said putative bleedthrough pixel mapping comprises alignment and skew adjusting said information with respect to said second image for said comparing with said putative bleedthrough pixel mapping.

26. The method of claim 20, wherein said processing said putative bleedthrough pixel mapping comprises deleting regions of putative bleedthrough pixels in said mapping smaller than a threshold value from said putative bleedthrough pixel mapping.

27. The method of claim 20, wherein said processing said putative bleedthrough pixel mapping comprises thinning regions of putative bleedthrough pixels in said mapping to thereby remove a portion of said regions.

28. The method of claim 20, wherein said replacing pixels of said first image comprises using quasi-random replacement pixels to replace said pixels of said first image corresponding to said putative bleedthrough pixels.

29. The method of claim 28, wherein said quasi-random replacement comprises using a distribution of a first type of pixels of said first image with respect to the replaced pixels.

31. The method of claim 20, further comprising analyzing said putative bleedthrough pixel mapping to determine if bleedthrough is present in said first image.

30. The method of claim 30, further comprising fattening regions of putative bleedthrough pixels in said mapping to thereby soften a visual impact associated with replacing pixels of said first image corresponding to said putative bleedthrough pixels.

32. A computer program product having a computer-readable medium having computer program logic recorded thereon for removing bleedthrough from an image, said computer program product comprising:

code for generating a putative bleedthrough pixel mapping for a first image;

code for processing said putative bleedthrough pixel mapping using information with respect to a second image, wherein said first image and said second image are associated with juxtaposed sides of a document; and

code for replacing pixels of said first image corresponding to putative bleedthrough pixels of said mapping.

33. The computer program product of claim 32, wherein said first image and said second image are at a different resolution, and further comprising code for scaling a resolution of one of said first and second images having a higher resolution down to a resolution of the other one of said first and second images.

34. The computer program product of claim 32, wherein said cod for processing said putative bleedthrough pixel mapping removes false positive bleedthrough pixels therefrom.

35. The computer program product of claim 32, wherein said code for processing said putative bleedthrough pixel mapping comprises code for adjusting alignment and skew of said information with respect to said second image for said comparing with said putative bleedthrough pixel mapping.

36. The computer program product of claim 35, wherein said code for processing said putative bleedthrough pixel mapping comprises code for comparing said alignment and skew adjusted information with respect to said second image to said putative bleedthrough pixel mapping and removing putative bleedthrough pixels from said mapping where there is no corresponding pixel in said second image.

37. The computer program product of claim 35, wherein said code for processing said putative bleedthrough pixel mapping further comprises code for deleting regions of putative bleedthrough pixels in said mapping smaller than a threshold value from said putative bleedthrough pixel mapping.

38. The computer program product of claim 35, wherein said code for processing said putative bleedthrough pixel mapping further comprises code for thinning regions of putative bleedthrough pixels in said mapping to thereby remove a portion of said regions.

39. The computer program product of claim 32, wherein said code for replacing pixels of said first image comprises code for using quasi-random replacement pixels to replace said pixels of said first image corresponding to said putative bleedthrough pixels, wherein said quasi-random replacement comprises using a distribution of a first type of pixels of said first image with respect to the replaced pixels.

40. The computer program product of claim 32, further comprising code for fattening regions of putative bleedthrough pixels in said mapping to thereby soften a visual impact associated with replacing pixels of said first image corresponding to said putative bleedthrough pixels.

41. The computer program product of claim 32, further comprising code for analyzing said putative bleedthrough pixel mapping to determine if bleedthrough is present in said first image.

42. A system for removing bleedthrough from an image, said system comprising:

means for generating a putative bleedthrough pixel mapping for a first image;

means for comparing information with respect to a second image to said putative bleedthrough pixel mapping; and

means for replacing pixels of said first image corresponding to putative bleedthrough pixels of said mapping using replacement pixels.

43. The system of claim 42, wherein said replacement pixels comprise quasi-random pixels.

44. The system of claim 42, further comprising means for adjusting an orientation of information with respect to said second image for said comparing with said putative bleedthrough pixel mapping.

45. The system of claim 42, further comprising means for processing said putative bleedthrough pixel mapping to remove false positive bleedthrough pixels from said mapping where there is no corresponding pixel in said second image.

46. The system of claim 45, wherein said means for processing said putative bleedthrough pixel mapping comprises means for deleting regions of putative bleedthrough pixels in said mapping smaller than a threshold value from said putative bleedthrough pixel mapping.

47. The system of claim 45, wherein said means for processing said putative bleedthrough pixel mapping comprises means for thinning regions of putative bleedthrough pixels in said mapping to thereby remove a portion of said regions.