IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND COMPUTER PROGRAM

• US 20100232690A1
• Filed: 06/23/2008
• Published: 09/16/2010
• Est. Priority Date: 06/29/2007
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Yamazaki, Taeko, Enomoto, Makoto, Kanatsu, Tomotoshi
• Granted Patent: US 8,503,773 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06V 30/10 Character recognition
• 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

An image processing apparatus includes a character recognition unit configured to perform character recognition on a plurality of character images in a document image to acquire a character code corresponding to each character image, and a generation unit configured to generate an electronic document, wherein the electronic document includes the document image, a plurality of character codes acquired by the character recognition unit, a plurality of glyphs, and data which indicates the glyphs to be used to render each of the character codes, wherein each of the plurality of glyphs is shared and used by different character codes based on the data when rendering characters that correspond to the plurality of character codes acquired by the recognition unit.

Claims

1. An image processing apparatus comprising:

a character recognition unit configured to perform character recognition on a plurality of character images in a document image to acquire a character code corresponding to each character image, and

a generation unit configured to generate an electronic document, wherein the electronic document includes the document image, a plurality of character codes acquired by the character recognition unit, a plurality of glyphs, and data which indicates the glyphs to be used to render each of the character codes,

wherein each of the plurality of glyphs is shared and used by different character codes based on the data when rendering characters that correspond to the plurality of character codes acquired by the recognition unit.

2. The image processing apparatus according to claim 1, further comprising a selection unit configured to select a glyph to be used for each character image from the plurality of glyphs, based on a character width and character row height of each character image in the document image,

wherein the data stored in the electronic document that indicates the glyphs to be used in rendering the character codes is described based on the glyph selected by the selection unit for each character image in the document image.

3. The image processing apparatus according to claim 1, further comprising a selection unit configured to select a glyph to be used for each character image from the plurality of glyphs, based on a character spacing and character row height of each character image in the document image,

wherein the data stored in the electronic document that indicates the glyphs to be used in rendering the character codes is described based on the glyph selected by the selection unit for each character image in the document image.

4. The image processing apparatus according to claim 1, wherein each of the glyphs has a different width.

5. The image processing apparatus according to claim 1, wherein each of the glyphs indicates a simple shape.

6. The image processing apparatus according to claim 1, wherein each of the glyphs indicates a rectangular shape.

7. The image processing apparatus according to claim 1, wherein each of the glyphs indicates shape of blank character.

8. The image processing apparatus according to claim 1, wherein the glyphs are rendered in the lower part of a character row.

9. The image processing apparatus according to claim 1, wherein the generation unit generates the electronic document that includes an average value of a distance between characters.

10. The image processing apparatus according to claim 1, wherein the electronic document generated by the generation unit includes a description for rendering the glyphs that correspond to the plurality of character codes in a transparent color at a position that approximately matches each character image in the document image.

11. The image processing apparatus according to claim 1, wherein the electronic document is generated in an XML format.

12. An image processing apparatus according to claim 1, wherein the electronic document is generated in an XPS format.

13. An image processing apparatus according to claim 1, further comprising a compression unit configured to compress the document image for storage in the electronic document.

14. The image processing apparatus according to claim 13, wherein the compression unit analyzes a region included in the document image and adaptively performs compression.

15. The image processing apparatus according to claim 1, further comprising a search unit configured to search the generated electronic document using an input keyword and to highlight a portion that matches the keyword.

16. The image processing apparatus according to claim 15, wherein the search unit highlights a portion matching the keyword by reversing a color of the matching portion.

17. A method comprising:

acquiring a character code corresponding to each character image by performing a character recognition on a plurality of character images in a document image, and

generating an electronic document, wherein the electronic document includes the document image, a plurality of character codes acquired by performing the character recognition, a plurality of glyphs, and data which indicates the glyphs to be used to render each of the character codes,

wherein each of the plurality of glyphs is shared and used by different character codes based on the data when rendering characters that correspond to the plurality of character codes acquired by performing the character recognition.

18. The method according to claim 17, further comprising selecting a glyph to be used for each character image from the plurality of glyphs, based on a character width and character row height of each character image in the document image,

wherein the data stored in the electronic document that indicates the glyphs to be used in rendering the character codes is described based on the glyph selected by the selection unit for each character image in the document image.

19. The method according to claim 17, further comprising selecting a glyph to be used for each character image from the plurality of glyphs, based on a character spacing and character row height of each character image in the document image,

wherein the data stored in the electronic document that indicates the glyphs to be used in rendering the character codes is described based on the glyph selected by the selection unit for each character image in the document image.

20. The method according to claim 17, wherein each of the glyphs has a different width.

21. The method according to claim 17, wherein each of the glyphs indicates a simple shape.

22. The method according to claim 17, wherein each of the glyphs indicates a rectangular shape.

23. The method according to claim 17, wherein each of the glyphs indicates shape of blank character.

24. A method according to claim 17, wherein the glyphs are rendered in the lower part of a character row.

25. The method according to claim 17, wherein the generated electronic document further includes an average value of a distance between characters.

26. The method according to claim 17, wherein the generated electronic document includes a description for rendering glyphs corresponding to the plurality of character codes in a transparent color at a position that approximately matches each character image in the document image.

27. A computer program stored in a computer-readable storage medium, the computer program causing a computer to execute steps of:

acquiring a character code corresponding to each character image by performing a character recognition on a plurality of character images in a document image, and

generating an electronic document, wherein the electronic document includes the document image, a plurality of character codes acquired by performing the character recognition, a plurality of glyphs, and data which indicates the glyphs to be used to render each of the character codes,

wherein each of the plurality of glyphs is shared and used by different character codes based on the data when rendering characters that correspond to the plurality of character codes acquired by performing the character recognition.