Method and apparatus for segmenting an image using a combination of image segmentation techniques

• US 20020076103A1
• Filed: 12/15/2000
• Published: 06/20/2002
• Est. Priority Date: 12/15/2000
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Banton, Martin E., Fuss, William A., Lin, Ying-Wei
• Granted Patent: US 6,941,014 B2
• Time in Patent Office: Days
• US Class Current: 382/173
• CPC Class Codes: G06T 2207/10008 from scanner, fax or copier
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/174 involving the use of two or more images
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: H04N 1/40062 Discrimination between different image types, e.g. two-tone, continuous tone
• CPC Class Codes: H04N 1/41 Bandwidth or redundancy reduction by scanning H04N1/17 ; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00

Abstract

This invention relates to a method and apparatus for segmenting an image using a combination of image segmentation techniques. More particularly, the invention is directed to an improved image segmentation technique for use in an image processing system that performs at least two distinct image segmentation processes on an image and combines the results to obtain a combined multi-layer representation of the image that can be suitably processed. In a specific example, a block based segmentation technique is performed on an image to generate a MRC (mixed raster content) representation—having foreground, background and selector layers. A pixel based segmentation technique is also performed on the image to generate rendering hints. The MRC representation and the rendering hints are then combined to obtain a four (4) layer representation of the image. The four layer representation is subsequently processed as required by the image processing system, e.g. compressed and stored.

Claims

1. A method for segmenting an image, the image comprising pixels and being represented by image data, the method comprising steps of:

obtaining image data;

inputting the image data into a first image segmentation module;

generating first segmentation data by the first image segmentation module, the first image segmentation data representing at least one first characteristic of the image data;

inputting the image data into a second image segmentation module;

generating second image segmentation data by the second image segmentation module, the second image segmentation data representing at least one second characteristic of the image data; and

,

integrating the first image segmentation data with the second image segmentation data to obtain modified image data.

2. The method as set forth in claim 1 wherein the inputting of the image data to the first image segmentation module and the inputting of the image data to the second image segmentation module are accomplished concurrently.

3. The method as set forth in claim 1 wherein the generating of the first image segmentation data comprises generating first characteristic data representing a background layer, a selector layer and a foreground layer of the image data.

4. The method as set forth in claim 1 wherein the generating of the second image segmentation data comprises generating second characteristic data representing rendering hints.

5. The method as set forth in claim 1 wherein the integrating of the first and second image segmentation data comprises generating the modified image data such that it comprises a background layer, a selector layer, and a foreground layer of the image data and a layer of information representing rendering hint for the image data.

6. A system for segmenting an image, the image comprising pixels and being represented by image data, the system comprising:

means for obtaining image data;

means for generating first segmentation data, the first image segmentation data representing at least one first characteristic of the image data;

means for generating second image segmentation data, the second image segmentation data representing at least one second characteristic of the image data; and

,

means for integrating the first image segmentation data with the second image segmentation data to obtain modified image data.

7. The system as set forth in claim 6 further comprising means for inputting the image data to the first image segmentation module and inputting the image data to the second image segmentation module concurrently.

8. The system as set forth in claim 6 wherein the first image segmentation data comprises first characteristic data representing a background layer, a selector layer and a foreground layer of the image data.

9. The system as set forth in claim 6 wherein the second image segmentation data comprises second characteristic data representing rendering hints.

10. The system as set forth in claim 6 wherein the modified image data comprises a background layer, a selector layer, and a foreground layer of the image data and a layer of information representing rendering hint for the image data.

11. The system as set forth in claim 6 wherein the means for generating the first segmentation data comprises a first segmentation module.

12. The system as set forth in claim 6 wherein the means for generating the second image segmentation data comprises a second image segmentation module.

13. The system as set forth in claim 11 wherein the first segmentation module comprises a block based image segmentation module.

14. The system as set forth in claim 11 wherein the first segmentation module comprises an object based image segmentation module.

15. The system as set forth in claim 12 wherein the second image segmentation module comprises a pixel based image segmentation module.

17. The system as set forth in claim 16 wherein the system is included in a xerographic printing environment.

18. The system as set forth in claim 16 wherein the print engine is a xerographic print engine.

19. The system as set forth in claim 16 wherein the first image segmentation data comprises first characteristic data representing a background layer, a selector layer and a foreground layer of the image data.

20. The system as set forth in claim 16 wherein the second image segmentation data comprises second characteristic data representing rendering hints.

21. The system as set forth in claim 16 wherein the first and second segmentation data comprises layers whereby an absence of a selected layer establishes a default position for a characteristic represented by the selected layer.

22. The system as set forth in claim 16 further comprising a third image segmentation module operative to generate third image segmentation data.

23. The system as set forth in claim 22 wherein the combining module is operative to combine the third image segmentation data with the first and second image segmentation data.

16. An image rendering system adapted for segmenting an image, the image comprising pixels and being represented by image data, the system comprising:

a scanner operative to obtain image data;

a bitmap generator operative to generate a bitmap corresponding to the image data;

a first image segmentation module operative to generate first image segmentation data, the first image segmentation data representing at least one first characteristic of the image data;

a second image segmentation module operative to generate second image segmentation data, the second image segmentation data representing at least one second characteristic of the image data;

a combining module operative to combine the first image segmentation data with the second image segmentation data to obtain modified image data;

a compression module operative to compress the modified image data;

a storage module operative to store the compressed image data;

a decompression module operative to decompress the stored image data; and

,

a print engine operative to render the image based on the decompressed data.