Image processing method, image processing apparatus and image processing program

• US 20040061883A1
• Filed: 09/23/2003
• Published: 04/01/2004
• Est. Priority Date: 09/30/2002
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Kanatsu, Tomotoshi
• Granted Patent: US 7,298,900 B2
• Time in Patent Office: Days
• US Class Current: 358/1.9
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

The present invention relates to an image processing method, an image processing apparatus and an image processing program for dealing with inverted characters (outlined characters) constituted by white pixels on a black ground in a tree structure same as that of normal characters constituted by black pixels on a white ground.

In the present invention, black pixel blocks and white pixel blocks are sampled recursively from a binary image, tree structure data indicating a positional relation between the sampled black pixel blocks and white pixel blocks is created, an inverted image is created by white-black-inverting the insides of black pixel blocks that can include inverted characters, of black pixel blocks included in the tree structure data, white pixel blocks and black pixel blacks are sampled from the created inverted image, and data regarding the sampled white pixel blocks and black pixel blocs is added to corresponding nodes of the tree structure data.

Claims

1. An image processing method comprising:

a first pixel block sampling step of recursively sampling black pixel blocks and white pixel blocks from a binary image;

a tree structure creating step of creating tree structure data indicating a positional relation between the black pixel blocks and white pixel blocks sampled in said first pixel block sampling step;

an inverted image creating step of creating an inverted image by white-black-inverting the insides of black pixel blocks that can include inverted characters, of black pixel blocks included in said tree structure data;

a second pixel block sampling step of sampling white pixel block and black pixel blocks from the inverted image created in said inverted image creating step; and

a tree structure addition step of adding data regarding the white pixel blocks and black pixel blocks sampled in said second pixel block sampling step to corresponding nodes of said tree structure data.

2. The image processing method according to claim 1, wherein for the data regarding the white pixel blocks and black pixel blocks added in said tree structure addition step, data regarding white pixel blocks having data regarding the sampled black pixel blocks as child nodes is added as child nodes of the white-black-inverted black pixel blocks of said tree structure data.

3. The image processing method according to claim 1, wherein in said inverted image creating step, said inverted image is created by white-black inverting the pixels inside the black pixel blocks sampled in said first pixel block sampling step with the outline of the black pixel blocks constituted by black pixels.

4. The image processing method according to claim 1, further comprising an area division step of dividing said binary image into a plurality of areas by grouping black pixel blocks based on the tree structure data with data regarding white pixel blocks and black pixel blocks added in said tree structure addition step.

5. The image processing method according to claim 1, further comprising an area tree structure creating step of creating area tree structure data indicating a positional relation between a plurality of areas by grouping black pixel blocks based on the tree structure data with data regarding white pixel blocks and black pixel blocks added in said tree structure addition step.

6. The image processing method according to claim 1, wherein said black pixel block is an area surrounded by a black pixel outline obtained by performing eight direction outline tracking of black pixels, and said white pixel block is an area surrounded by white pixel outline obtained by performing four direction outline tracking of white pixels.

7. The image processing method according to claim 1, wherein said binary image is an image obtained by subjecting a binary original image to OR scaledown, and

said inverted image is created based on the area of black pixel blocks to be white-black-inverted and an image obtained by white-black inverting said original image and subjecting the same to OR scaledown.

8. The image processing method according to claim 1, wherein in said inverted image creating step, an inverted image for black pixel blocks of low black pixel density, of black pixel blocks included in said tree structure data, is not created.

9. The image processing method according to claim 1, wherein the black pixel blocks sampled in said second pixel block sampling step are black pixel blocks remaining after removing black pixel blocks sampled from said inverted image that are located at positions corresponding to white pixel blocks each having a predetermined size or greater size, of white pixel blocks sampled from said binary image, from a plurality of black pixel blocks sampled from said inverted image.

10. The image processing method according to claim 1, wherein in said second pixel block sampling step, it is determined that black pixel blocks from which the inverted image is created include no inverted characters to end processing if the ratio of black pixel blocks originating from noises to a plurality of black pixel blocks extracted from said inverted image equals a predetermined value or greater value.

11. The image processing method according to claim 7, wherein said binary original image is an image converted by binarizing a multi-valued original image.

12. An image processing apparatus comprising:

first pixel block sampling means for recursively sampling black pixel blocks and white pixel blocks from a binary image;

tree structure creating means for creating tree structure data indicating a positional relation between the black pixel blocks and white pixel blocks sampled by said first pixel block sampling means;

inverted image creating means for creating an inverted image by white-black-inverting the insides of black pixel blocks that can include inverted characters, of black pixel blocks included in said tree structure data;

second pixel block sampling means for sampling white pixel block and black pixel blocks from the inverted image created by said inverted image creating means; and

tree structure addition means for adding data regarding the white pixel blocks and black pixel blocks sampled by said second pixel block sampling means to corresponding nodes of said tree structure data.

13. The image processing apparatus according to claim 12, wherein for the data regarding the white pixel blocks and black pixel blocks added by said tree structure addition means, data regarding white pixel blocks having data regarding the sampled black pixel blocks as child nodes is added as child nodes of the white-black-inverted black pixel blocks of said tree structure data.

14. The image processing apparatus according to claim 12, wherein said inverted image creating means creates said inverted image by white-black inverting the pixels inside the black pixel blocks sampled by said first pixel block sampling means with the outline of the black pixel blocks constituted by black pixels.

15. The image processing apparatus according to claim 12, further comprising area division means for dividing said binary image into a plurality of areas by grouping black pixel blocks based on the tree structure data with data regarding white pixel blocks and black pixel blocks added by said tree structure addition means.

16. The image processing apparatus according to claim 12, further comprising area tree structure creating means for creating area tree structure data indicating a positional relation between a plurality of areas by grouping black pixel blocks based on the tree structure data with data regarding white pixel blocks and black pixel blocks added by said tree structure addition means.

17. The image processing apparatus according to claim 12, wherein said black pixel block is an area surrounded by a black pixel outline obtained by performing eight direction outline tracking of black pixels, and said white pixel block is an area surrounded by white pixel outline obtained by performing four direction outline tracking of white pixels.

18. The image processing apparatus according to claim 12, wherein said binary image is an image obtained by subjecting a binary original image to OR scaledown, and

said inverted image is created based on the area of black pixel blocks to be white-black-inverted and an image obtained by white-black inverting said original image and subjecting the same to OR scaledown.

19. The image processing apparatus according to claim 12, wherein said inverted image creating means does not create an inverted image for black pixel blocks of low black pixel density, of black pixel blocks included in said tree structure data.

20. The image processing apparatus according to claim 12, wherein the black pixel blocks sampled by said second pixel block sampling means are black pixel blocks remaining after removing black pixel blocks sampled from said inverted image that are located at positions corresponding to white pixel blocks each having a predetermined size or greater size, of white pixel blocks sampled from said binary image, from a plurality of black pixel blocks sampled from said inverted image.

21. The image processing apparatus according to claim 12, wherein said second pixel block sampling means determines that black pixel blocks from which the inverted image is created include no inverted characters to end processing if the ratio of black pixel blocks originating from noises to a plurality of black pixel blocks extracted from said inverted image equals a predetermined value or greater value.

22. The image processing apparatus according to claim 18, wherein said binary original image is an image converted by binarizing a multi-valued original image.

23. A computer executable image processing program comprised of codes for making a computer perform:

a first pixel block sampling step of recursively sampling black pixel blocks and white pixel blocks from a binary image;

a tree structure creating step of creating tree structure data indicating a positional relation between the black pixel blocks and white pixel blocks sampled in said first pixel block sampling step;

an inverted image creating step of creating an inverted image by white-black-inverting the insides of black pixel blocks that can include inverted characters, of black pixel blocks included in said tree structure data;

a second pixel block sampling step of sampling white pixel block and black pixel blocks from the inverted image created in said inverted image creating step; and

a tree structure addition step of adding data regarding the white pixel blocks and black pixel blocks sampled in said second pixel block sampling step to corresponding nodes of said tree structure data.

24. A storage medium including a computer readable image processing program, the image processing program comprised of codes for making a computer perform:

a first pixel block sampling step of recursively sampling black pixel blocks and white pixel blocks from a binary image;

a tree structure creating step of creating tree structure data indicating a positional relation between the black pixel blocks and white pixel blocks sampled in said first pixel block sampling step;

an inverted image creating step of creating an inverted image by white-black-inverting the insides of black pixel blocks that can include inverted characters, of black pixel blocks included in said tree structure data;

a second pixel block sampling step of sampling white pixel block and black pixel blocks from the inverted image created in said inverted image creating step; and

a tree structure addition step of adding data regarding the white pixel blocks and black pixel blocs sampled in said second pixel block sampling step to corresponding nodes of said tree structure data.