Method and system for classifying and processing of pixels of image data

• US 6,347,153 B1
• Filed: 09/23/1998
• Issued: 02/12/2002
• Est. Priority Date: 01/21/1998
• Status: Expired due to Term

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Clark, Raymond J., Shiau, Jeng-Nan, Triplett, Roger L.
• Primary Examiner(s): Johns, Andrew W.
• Assistant Examiner(s): AZARIAN, SEYED H
• Application Number:
  US09/159,534
• Time in Patent Office: 1,238 Days
• Field of Search: 382/224, 382/225, 382/226, 382/227, 382/228, 382/230, 382/299, 358/455, 358/456, 358/458, 358/462, 358/464
• US Class Current: 382/224
• CPC Class Codes: G06T 2207/10008 from scanner, fax or copier
• CPC Class Codes: G06T 7/44 using image operators, e.g. filters, edge density metrics or local histograms
• CPC Class Codes: H04N 1/40062 Discrimination between different image types, e.g. two-tone, continuous tone

Abstract

A system and method classify a pixel of image data as one of a plurality of image types. A first image characteristic value for the pixel, a second image characteristic value for the pixel, a third image characteristic value for the pixel, and a fourth image characteristic for the pixel is determined. Some of these determinations may be resolution dependent. The values from these determination are utilized in assigning an image type classification to the pixel. An auto-segmentation circuit enables classifying a pixel as a continuous tone and detecting a gradient in the window of pixels of which the pixel is a member. A filter enhances the image data of the pixel tone when a gradient indicating that image data within the window of pixels is changing at a rate greater than a predetermined threshold is detected or lowpasses the image data of the pixel tone when a gradient indicating that image data within the window of pixels is changing at a rate less than a predetermined threshold is detected.

Claims

1. A method for determining a continuous tone classification type of a pixel of image data in a window of pixels, comprising the steps of:

(a) classifying the pixel as representing a continuous tone;

(b) detecting a gradient in the window of pixels of which the pixel is a member; and

(c) classifying the pixel as a rough continuous tone when said step (b) detects a gradient indicating that image data within the window of pixels is changing at a rate greater than a predetermined threshold.

2. The method as claimed in claim 1, further comprising the step of:

(d) classifying the pixel as a smooth continuous tone when said step (b) detects a gradient indicating that image data within the window of pixels is changing at a rate less than the predetermined threshold.

3. The method as claimed in claim 1, wherein said step (a) classifies the pixel manually through a user interface.

4. The method as claimed in claim 1, wherein said step (a) classifies the pixel automatically based on histogram information.

5. The method as claimed in claim 2, wherein said step (a) classifies the pixel manually through a user interface.

6. The method as claimed in claim 2, wherein said step (a) classifies the pixel automatically based on histogram information.

7. The method a claimed in claim 1, wherein said gradient is measured based on a sum of the Laplacians for pixels within the window.

8. The method a claimed in claim 2, wherein said gradient is measured based on a sum of the Laplacians for pixels within the window.

9. A system for determining a continuous tone classification type of a pixel of image data in a window of pixels, comprising:

an auto-segmentation circuit to enable classifying a pixel as a continuous tone; and

means for detecting a gradient in the window of pixels of which the pixel is a member;

said auto-segmentation circuit classifying the pixel as a rough continuous tone when a gradient indicating that image data within the window of pixels is changing at a rate greater than a predetermined threshold is detected.

10. The system as claimed in claim 9, wherein said auto-segmentation circuit classifies the pixel as a smooth continuous tone when a gradient indicating that image data within the window of pixels is changing at a rate less than a predetermined threshold is detected.

11. The system as claimed in claim 9, further comprising:

an user interface which enables an user to classify the pixel manually.

12. The system as claimed in claim 9, wherein said auto-segmentation circuit classifies the pixel automatically based on histogram information.

13. The system as claimed in claim 10, further comprising:

an user interface which enables an user to classify the pixel manually.

14. The system as claimed in claim 10, wherein said auto-segmentation circuit classifies the pixel automatically based on histogram information.

15. The system a claimed in claim 9, wherein said gradient is measured based on a sum of the Laplacians for pixels within the window.

16. The system a claimed in claim 10, wherein said gradient is measured based on a sum of the Laplacians for pixels within the window.

17. A rendering system for processing a pixel of image data in a window of pixels based on a continuous tone classification type, comprising:

an auto-segmentation circuit to enable classifying a pixel as a continuous tone;

means for detecting a gradient in the window of pixels of which the pixel is a member; and

a filter to enhance the image data of the pixel tone when a gradient indicating that image data within the window of pixels is changing at a rate greater than a predetermined threshold is detected.

18. The rendering system as claimed in claim 17, wherein said filter low-passes the image data of the pixel tone when a gradient indicating that image data within the window of pixels is changing at a rate less than a predetermined threshold is detected.

19. The rendering system as claimed in claim 17, further comprising:

an user interface which enables an user to classify the pixel manually.

20. The rendering system as claimed in claim 18, wherein said auto-segmentation circuit classifies the pixel automatically based on histogram information.

21. The rendering system as claimed in claim 17, further comprising:

an user interface which enables an user to classify the pixel manually.

22. The rendering system as claimed in claim 18, wherein said auto-segmentation circuit classifies the pixel automatically based on histogram information.

23. The rendering system a claimed in claim 17, wherein said gradient is measured based on a sum of the Laplacians for pixels within the window.

24. The rendering system a claimed in claim 18, wherein said gradient is measured based on a sum of the Laplacians for pixels within the window.

25. A method for determining a continuous tone classification type of a pixel of image data in a window of pixels, comprising the steps of:

(a) classifying the pixel as representing a continuous tone;

(b) detecting a gradient in the window of pixels of which the pixel is a member; and

(c) classifying the pixel as a smooth continuous tone when said step (b) detects a gradient indicating that image data within the window of pixels is changing at a rate less than a predetermined threshold.

26. A system for determining a continuous tone classification type of a pixel of image data in a window of pixels, comprising:

an auto-segmentation circuit to enable classifying a pixel as a continuous tone; and

means for detecting a gradient in the window of pixels of which the pixel is a member;

wherein said auto-segmentation circuit classifies the pixel as a smooth continuous tone when a gradient indicating that image data within the window of pixels is changing at a rate less than a predetermined threshold is detected.

27. A rendering system for processing a pixel of image data in a window of pixels based on a continuous tone classification type, comprising:

an auto-segmentation circuit to enable classifying a pixel as a continuous tone;

means for detecting a gradient in the window of pixels of which the pixel is a member; and

a filter to lowpass the image data of the pixel tone when a gradient indicating that image data within the window of pixels is changing at a rate less than a predetermined threshold is detected.