Image processing apparatus, method, storage medium and program

• US 20040220962A1
• Filed: 04/27/2004
• Published: 11/04/2004
• Est. Priority Date: 04/30/2003
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Kaneda, Kitahiro
• Granted Patent: US 7,548,916 B2
• Time in Patent Office: Days
• US Class Current: 707/102
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

Retrieval accuracy is improved by causing a difference in layout from document to document to be reflected in retrieval at will. To achieve this, there is provided an information processing method for a case having a plurality of retrieval steps (S1209, S1211, S1212) of retrieving image data that is similar to an input document image, the method including a step (S1200) of inputting weighting information for weighting a degree of similarity calculated by each of the retrieval steps; a step of weighting the degree of similarity, which has been calculated by each of the retrieval steps, for every item of image data on the basis of the weighting information, and calculating overall degree of similarity; and a step (S1213) of displaying the similar image data based upon the overall degree of similarity calculated.

Claims

1. An information processing apparatus having a plurality of retrieval unit adapted to calculate a degree of similarity for each stored image data that is similar to an input document image, comprising:

input unit adapted to input priority information for weighting a degree of similarity calculated by each of said retrieval unit;

calculation unit adapted to calculate overall degrees of similarity between the input document image and each stored image data by weighting, on the basis of the priority information, the degree of similarity which has been calculated by each of said retrieval unit; and

display unit adapted to display the similar image data based upon the overall degree of similarity calculated by said calculation unit.

2. The apparatus according to claim 1, wherein said display unit sorts and displays, in order of decreasing overall degree of similarity, information relating to the overall degree of similarity of each item of image data and information relating to retrieval unit that have influenced this overall degree of similarity.

3. The apparatus according to claim 1, wherein said display unit displays the overall degree of similarity of the similar image data in the form of a graph.

4. The apparatus according to claim 1, wherein said display unit further displays, for each of the displayed image data, types of retrieval unit that have influenced the overall degree of similarity.

5. The apparatus according to claim 1, further comprising segmentation unit adapted to segment the input document image into areas on a per-attribute basis;

wherein said plurality of retrieval unit include;

unit adapted to conduct a full-text search, which is based upon text data extracted by character recognition from a text area, from among the areas obtained by segmentation by said segmentation unit;

unit adapted to conduct a concept search based upon the text data; and

unit adapted to conduct an image search, which is based upon a feature extracted from an image area, from among the areas obtained by segmentation by said segmentation unit.

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

segmentation unit adapted to segment the input document image into areas on a per-attribute basis; and

search-area designating unit adapted to designate, based upon a command from the user, an area to be used in the search by each of said retrieval unit from among the areas segmented by said segmentation unit;

wherein said calculation unit obtains the degree of similarity with regard to an area designated by said search-area designating unit, applies weighting to the degree of similarity obtained and calculates overall degree of similarity.

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

segmentation unit adapted to segment the input document image into areas on a per-attribute basis; and

area designating unit adapted to designate, based upon a command from the user, an area to be emphasized at the time of retrieval from among the areas obtained by segmentation by said segmentation unit;

wherein said calculation unit enlarges weighting of an area that has been designated by said area designating unit and then calculates the overall degree of similarity.

8. The apparatus according to claim 1, further comprising conversion unit for converting the input document image to vector data if the overall degree of similarity that has been calculated by said calculation unit is equal to or less than a predetermined value.

9. The apparatus according to claim 8, wherein said conversion unit includes character recognition unit adapted to recognize characters in the input document image.

10. The apparatus according to claim 8, further comprising segmentation unit adapted to segment the input document image into areas on a per-attribute basis;

wherein said conversion unit converts the input document image to vector data for every area obtained by segmentation by said segmentation unit.

11. An information processing method for a case having a plurality of retrieval steps of calculating a degree of similarity for each stored image data that is similar to an input document image, comprising:

an input step of inputting priority information for weighting a degree of similarity calculated by each of said retrieval steps;

a calculation step of calculating overall degrees of similarity between the input document image and each stored image data by weighting, on the basis of the priority information, the degree of similarity which has been calculated by each of said retrieval steps; and

a display step of displaying the similar image data based upon the overall degree of similarity calculated in said calculation step.

12. The method according to claim 11, wherein said display step sorts and displays, in order of decreasing overall degree of similarity, information relating to the overall degree of similarity of each item of image data and information relating to retrieval steps that have influenced this overall degree of similarity.

13. The method according to claim 11, wherein said display step displays the overall degree of similarity of the similar image data in the form of a graph.

14. The method according to claim 11, wherein said display step further displays, for each of the displayed image data, types of retrieval means that have influenced the overall degree of similarity.

15. The method according to claim 11, further comprising a segmentation step of segmenting the input document image into areas on a per-attribute basis;

wherein said plurality of retrieval steps include;

a step of conducting a full-text search, which is based upon text data extracted by character recognition from a text area, from among the areas obtained by segmentation by said segmentation step;

a step of conducting a concept search based upon the text data; and

a step of conducting an image search, which is based upon a feature extracted from an image area, from among the areas obtained by segmentation by said segmentation step.

16. The method according to claim 11, further comprising:

a segmentation step of segmenting the input document image into areas on a per-attribute basis; and

a search-area designating step of designating, based upon a command from the user, an area to be used in the search by each of said retrieval steps from among the areas obtained by segmentation by said segmentation step;

wherein said calculation step obtains the degree of similarity with regard to an area designated by said search-area designating step, applies weighting to the degree of similarity obtained and calculates overall degree of similarity.

17. The method according to claim 11, further comprising:

a segmentation step of segmenting the input document image into areas on a per-attribute basis; and

an area designating step of designating, based upon a command from the user, an area to be emphasized at the time of retrieval from among the areas obtained by segmentation by said segmentation step;

wherein said calculation step enlarges weighting of an area that has been designated by said area designating step and then calculates the overall degree of similarity.

18. The method according to claim 11, further comprising a conversion step of converting the input document image to vector data if the overall degree of similarity that has been calculated by said calculation step is equal to or less than a predetermined value.

19. The method according to claim 18, wherein said conversion step includes a character recognition step of recognizing characters in the input document image.

20. The method according to claim 18, further comprising a segmentation step of segmenting the input document image into areas on a per-attribute basis;

wherein said conversion step converts the input document image to vector data for every area obtained by segmentation by said segmentation step.

21. A storage medium storing a control program for causing the information processing method set forth in claim 11 to be implemented by a computer.

22. A control program for causing the information processing method set forth in claim 11 to be implemented by a computer.

23. An information processing apparatus having a plurality of retrieval unit adapted to calculate a degree of similarity for each stored image data that is similar to an input document image, comprising:

calculation unit for calculating overall degrees of similarity between the input document image and each stored image data by weighting degree of similarity which has been calculated by each of said retrieval unit; and

display unit adapted to display the similar image data and overall degrees of similarity of respective ones of items of the image data upon sorting these in order of decreasing overall degree of similarity calculated.

24. An information processing apparatus having a plurality of retrieval unit adapted to calculate a degree of similarity for each stored image data that is similar to desired area of an input document image, comprising:

segmentation unit adapted to segment the input document image into areas on a per-attribute basis;

search-area designating unit adapted to designate, based upon a command from the user, an area to be used in the search by each of said retrieval unit from among the areas segmented by said segmentation unit;

calculation unit adapted to calculate overall degrees of similarity between the designated area and each stored image data by weighting the degree of similarity calculated by each of said retrieval unit; and

display unit adapted to display similar image data based upon the overall degree of similarity calculated by said calculation unit.

25. An information processing apparatus having a plurality of retrieval unit adapted to calculate a degree of similarity for each stored image data that is similar to desired area of an input document image, comprising:

segmentation unit adapted to segment the input document image into areas on a per-attribute basis;

area designating unit adapted to designate, based upon a command from the user, an area to be emphasized at the time of retrieval from among the areas obtained by segmentation by said segmentation unit;

calculation unit adapted to calculate overall degrees of similarity between the segmented areas and each stored image data by weighting the degree of similarity calculated by each of said retrieval unit based on priority information for weighting an area designated by said area designating unit and priority information for weighting each of said retrieval unit; and

display unit adapted to display similar image data based upon the overall degree of similarity calculated by said calculation unit.

26. An information processing method for a case having a plurality of retrieval steps of calculating a degree of similarity for each stored image data that is similar to an input document image, comprising:

a calculation step of calculating overall degrees of similarity between the input document image and each stored image data by weighting degree of similarity which has been calculated by each of said retrieval steps; and

a display step of displaying similar image data and overall degrees of similarity of respective ones of items of the image data upon sorting these in order of decreasing overall degree of similarity calculated.

27. An information processing method for a case having a plurality of retrieval steps of calculating a degree of similarity for each stored image data that is similar to desired area of an input document image, comprising:

a segmentation step of segmenting the input document image into areas on a per-attribute basis;

a search-area designating step of designating, based upon a command from the user, an area to be used in the search by each of said retrieval steps from among the areas segmented by said segmentation step;

a calculation step of calculating overall degrees of similarity between the designated area and each stored image data by weighting the degree of similarity calculated by each of said retrieval steps; and

a display step of displaying similar image data based upon the overall degree of similarity calculated in said calculation step.

28. An information processing method for a case having a plurality of retrieval steps for calculating a degree of similarity for each stored image data that is similar to desired area of an input document image, comprising:

a segmentation step of segmenting the input document image into areas on a per-attribute basis;

an area designating step of designating, based upon a command from the user, an area to be emphasized at the time of retrieval from among the areas obtained by segmentation by said segmentation step;

a calculation step of calculating overall degrees of similarity between the segmented areas and each stored image data by weighting the degree of similarity calculated by each of said retrieval steps based on priority information for weighting an area designated by said area designating step and priority information for weighting each of said retrieval steps; and

a display step of displaying similar image data based upon the overall degree of similarity calculated in said calculation step.