Document processing apparatus and method

• US 20020085243A1
• Filed: 12/13/2001
• Published: 07/04/2002
• Est. Priority Date: 12/21/2000
• Status: Active Grant

• Current Assignee: Canon Ayutthaya Limited (Canon Inc.)
• Original Assignee: Canon Ayutthaya Limited (Canon Inc.)
• Inventors: Kanatsu, Tomotoshi
• Granted Patent: US 7,170,647 B2
• Time in Patent Office: Days
• US Class Current: 358/453
• CPC Class Codes: H04N 1/56 Processing of colour picture signals H04N1/52 takes precedence

Abstract

A document processing apparatus for segmenting a color document image into regions obtains a binary image by binarizing a color image, and extracts regions having different background colors from the color image to generate region information indicating the position and size of each extracted region. By making region segmentation on the basis of the binary image and region information, a region segmentation result that reflects the background colors can be obtained. In this way, region segmentation which can maintain region differences expressed by colors in a color document can be implemented.

Claims

1. A document processing apparatus comprising:

generation means for extracting a region having a different background color from a color image, and generating region information indicating a position and size of the region;

binarization means for binarizing the color image to obtain binary image data; and

segmentation processing means for performing region segmentation on the basis of the binary image data obtained by said binarization means and the region information generated by said generation means.

2. The apparatus according to claim 1, wherein said generation means extracts the region having the different background color on the basis of a plurality of binary images obtained by binarizing the color image using a plurality of threshold values.

3. The apparatus according to claim 2, wherein said generation means determines a black region larger than a predetermined size in each of the plurality of binary images as the region having the different background color.

4. The apparatus according to claim 2, wherein said generation means sets the plurality of threshold values on the basis of a luminance distribution of the color image.

5. The apparatus according to claim 2, wherein said binarization means executes a binarization process for the black region larger than the predetermined size.

6. The apparatus according to claim 5, wherein said binarization means comprises:

setting means for setting a binarization threshold value for a partial region of the color image corresponding to each black region extracted by said generation means, and

said binarization means generates the binary image of the color image by binarizing the partial region using the set threshold value.

7. The apparatus according to claim 6, wherein said binarization means comprises:

determination means for determining if black and white levels of the partial region of the color image corresponding to the black region extracted by said generation means are to be inverted, and

said binarization means performs binarization with the black and white levels being inverted.

8. The apparatus according to claim 1, wherein said segmentation processing means performs region segmentation under an assumption that a frame is present at the position of the region indicated by the region information.

9. The apparatus according to claim 1, further comprising:

forming means for forming a tree structure by extracting document elements from the binary image data obtained by said binarization means; and

changing means for changing the tree structure by forming a partial tree structure which has the document elements included in the region indicated by the region information as children connected to a parent indicating that region, and

wherein region segmentation is made on the basis of the tree structure obtained by said forming means and said changing means.

10. A document processing method comprising:

the generation step of extracting a region having a different background color from a color image, and generating region information indicating a position and size of the region;

the binarization step of binarizing the color image to obtain binary image data; and

the segmentation processing step of performing region segmentation on the basis of the binary image data obtained in the binarization step and the region information generated in the generation step.

11. The method according to claim 10, wherein the generation step includes the step of extracting the region having the different background color on the basis of a plurality of binary images obtained by binarizing the color image using a plurality of threshold values.

12. The method according to claim 11, wherein the generation step includes the step of determining a black region larger than a predetermined size in each of the plurality of binary images as the region having the different background color.

13. The method according to claim 11, wherein the generation step includes the step of setting the plurality of threshold values on the basis of a luminance distribution of the color image.

14. The method according to claim 11, wherein the binarization step includes the step of executing a binarization process for the black region larger than the predetermined size.

15. The method according to claim 14, wherein the binarization step comprises:

the setting step of setting a binarization threshold value for a partial region of the color image corresponding to each black region extracted in the generation step, and

the binarization step includes the step of generating the binary image of the color image by binarizing the partial region using the set threshold value.

16. The method according to claim 15, wherein the binarization step comprises:

the determination step of determining if black and white levels of the partial region of the color image corresponding to the black region extracted in the generation step are to be inverted, and

the binarization step includes the step of performing binarization with the black and white levels being inverted.

17. The method according to claim 10, wherein the segmentation processing step includes the step of performing region segmentation under an assumption that a frame is present at the position of the region indicated by the region information.

18. The method according to claim 10, further comprising:

the forming step of forming a tree structure by extracting document elements from the binary image data obtained in the binarization step; and

the changing step of changing the tree structure by forming a partial tree structure which has the document elements included in the region indicated by the region information as children connected to a parent indicating that region, and

wherein region segmentation is made on the basis of the tree structure obtained in the forming step and the changing step.

19. A storage medium that stores a control program for making a computer to execute a document process, said document process comprising:

the generation step of extracting a region having a different background color from a color image, and generating region information indicating a position and size of the region;

the binarization step of binarizing the color image to obtain binary image data; and

the segmentation processing step of performing region segmentation on the basis of the binary image data obtained in the binarization step and the region information generated in the generation step.