Image processing method and system

• US 20040213458A1
• Filed: 04/21/2004
• Published: 10/28/2004
• Est. Priority Date: 04/25/2003
• Status: Abandoned Application

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Kanatsu, Tomotoshi
• Application Number:
  US10/828,470
• Publication Number:
  US 20040213458A1
• Time in Patent Office: Days
• US Class Current: 382/181
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1444 Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
• 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 method and system for search for an original data file corresponding to an input image are provided. According to an image processing method associated with one aspect of the present invention, for example, first search information associated with an input image is acquired on the basis of the information input by a user, and feature data contained in the input image is acquired as second search information. Thereafter, an original data file corresponding to the input image is searched for by using the first and second search information. This makes it possible to improve the search performance in searching for an original data file corresponding to a paper document.

Claims

1. An image processing method for search for an, original data file corresponding to an input image, comprising the steps of:

(a) acquiring first search information associated with the input image on the basis of information input by a user;

(b) acquiring feature data contained in the input image as second search information; and

(c) searching for an original data file corresponding to the input image by using the first and second search information.

2. The method according to claim 1, further comprising the step of:

(d) registering the first search information as an index for searching for the original data file in an index file.

3. The method according to claim 1, wherein the first search information comprises a keyword for search.

4. The method according to claim. 1, wherein the first search information comprises a data size of the original data file.

5. The method according to claim 1, wherein the first search information comprises date information of the original data file.

6. The method according to claim 1, wherein the second search information comprises information associated with a storage location of the original data file which is extracted on the basis of pointer information in the input image.

7. The method according to claim 1, wherein the second search information comprises a character code of a character recognition result which is obtained by performing a character recognition process with respect to a character region in the input image.

8. The method according to claim 1, wherein the second search information comprises feature data of each block obtained by region segmentation of the input image.

9. The method according to claim 1, further comprising the step of:

(e) converting the input image into vector data when no original data file can be searched in the step (c).

10. The method according to claim 9, further comprising the step of:

(f) converting the input image, which has been converted into the vector data, into data in a format which can be handled by application software.

11. The method according to claim 9, further comprising the step of:

(g) storing the input image which has been converted into the vector data in a database.

12. The method according to claim 10, further comprising the step of:

(h) registering the first search information, in an index file, as an index for searching for an image represented by vector data stored in a database in the step (c).

13. The method according to claim 1, further comprising the step of:

(i) outputting the searched original data, wherein pointer information is added to the output original data file.

14. The method according to claim 13, wherein the pointer information is added as a digital watermark to the original data file.

15. The method according to claim 1, wherein in the step (c), the original data file is searched for by using at least one of keyword search, full-text search, and layout search.

16. An image processing system which searches for an original data file corresponding to an input image, comprising:

means for acquiring first search information associated with the input image on the basis of information input by a user;

means for acquiring feature data contained in the input image as second search information; and

means for searching for an original data file corresponding to the input image by using the first and second search information.

17. A computer executable program stored on a computer-readable medium for search for an original data file corresponding to an input image, comprising:

code for acquiring first search information associated with the input image on the basis of information input by a user;

code for acquiring feature data contained in the input image as second search information; and

code for searching for an original data file corresponding to the input image by using the first and second search information.

18. A computer-readable medium having a computer executable program stored thereon for search for an original data file corresponding to an input image, the program comprising:

code for acquiring first search information associated with the input image on the basis of information input by a user;

code for acquiring feature data contained in the input image as second search information; and

code for searching for an original data file corresponding to the input image by using the first and second search information.