Identifying key images in a document in correspondence to document text

• US 6,904,560 B1
• Filed: 03/23/2000
• Issued: 06/07/2005
• Est. Priority Date: 03/23/2000
• Status: Expired due to Term

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Panda, Chinmoy
• Primary Examiner(s): Feild, Joseph
• Assistant Examiner(s): Smith, Peter J.
• Application Number:
  US09/535,441
• Time in Patent Office: 1,902 Days
• Field of Search: 715/501.1, 707/3, 707/4, 707/104.1
• US Class Current: 715/202
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 40/106 Display of layout of documents; Previewing

Abstract

A computer-implemented method and system for identifying key images in a document is provided. The operations used include extracting one or more document keywords from the document considered important in describing the document, collecting one or more images associated with the document including information describing each image, generating a proximity factor for each image collected from the document and each document keyword that reflects the degree of correlation between the image and the document keyword, and determining the importance of each image according to an image metric that combines the proximity factors for each document keyword and image pair. In addition, the operations may also include ordering the document keywords according to an ordering criterion and weighting the proximity factor associated with each document keyword and image pair based on the order of the document keyword.

Claims

1. A computer-implemented method, comprising:

receiving a document comprising text and a plurality of images, each of the plurality of images having a location in the document;

extracting one or more document keywords from the document;

generating a proximity factor for each pair of one of the plurality of images and one of the document keywords, the proximity factor reflecting a degree of correlation between the image and the document keyword of the pair; and

determining the importance of each of the plurality of images according to an image metric that combines the proximity factors for each document keyword and image pair.

2. The method of claim 1 further comprising presenting one or more of the plurality of images determined to be important on a display device.

3. The method of claim 1 further comprising:

ordering the document keywords according to an ordering criterion; and

weighting the proximity factor associated with each document keyword and image pair based on the order of the document keyword.

4. The method of claim 3 wherein the frequency that each document keyword appears in the document determines the ordering criterion used to order the document keywords.

5. The method of claim 3 wherein the document has a subject matter and the ordering criterion orders the document keywords according to their relationship with the subject matter of the document.

6. The method of claim 1 further comprising identifying image text associated with each image of the plurality of images.

7. The method of claim 6 wherein identifying image text comprises:

scanning a bit-mapped representation of the image for text information; and

converting the bit-mapped representation of the text information into image text.

8. The method of claim 6 wherein identifying image text comprises:

searching metadata information associated with the image for text describing the image.

9. The method of claim 8 wherein the metadata information is compatible with hypertext markup language (HTML).

10. The method of claim 6 wherein generating the proximity factor for an image and a document keyword of a document keyword and image pair further comprises lexically analyzing the image text associated with the image and the document keyword to determine the degree of correlation between the image and the document keyword.

11. The method of claim 6 wherein generating the proximity factor for an image and a document keyword of a document keyword and image pair further comprises performing a phonetic comparison between the image text associated with the image and the document keyword to determine the degree of correlation between the image and the document keyword.

12. The method of claim 1 wherein generating the proximity factor for an image and a document keyword of a document keyword and image pair further comprises:

identifying the location of the image in the document;

measuring the distance in the document between the image and the document keyword; and

determining the correlation between the document keyword and the image according to the distance between the document keyword and the image.

13. An apparatus comprising:

means for receiving a document comprising text and a plurality of images, each of the plurality of images having a location in the document;

means for extracting one or more document keywords from the document;

means for generating a proximity factor for each pair of one of the plurality of images and one of the document keywords, the proximity factor reflecting a degree of correlation between the image and the document keyword of the pair; and

means for determining the importance of each of the plurality of images according to an image metric that combines the proximity factors for each document keyword and image pair.

14. The apparatus of claim 13, further comprising:

means for ordering the document keywords according to an ordering criterion; and

means for weighting the proximity factor associated with each document keyword and image pair based on the order of the document keyword.

15. A computer program product, tangibly embodied in a machine-readable storage device, the product comprising instructions operable to cause a computer to:

receive a document comprising text and a plurality of images, each of the plurality of images having a location in the document;

extract one or more document keywords from the document;

generate a proximity factor for each pair of one of the plurality of images and one of the document keywords, the proximity factor reflecting a degree of correlation between the image and the document keyword of the pair; and

determine the importance of each of the plurality of images according to an image metric that combines the proximity factors for each document keyword and image pair.

16. The product of claim 15 further comprising instructions to:

present one or more of the plurality of images determined to be important on a display device.

17. The product of claim 15 further comprising instruction to:

order the document keywords according to an ordering criterion; and

weigh the proximity factor associated with each document keyword and image pair based on the order of the document keyword.

18. The product of claim 17 wherein the frequency that each document keyword appears in the document determines the ordering criterion used to order the document keywords.

19. The product of claim 17 wherein the document has a subject matter and the ordering criterion orders the document keywords according to their relationship with the subject matter of the document.

20. The product of claim 15 further comprising instructions to identify image text associated with each image of the plurality of images.

21. The product of claim 20 wherein the instructions to identify image text comprise instructions to:

scan a bit-mapped representation of the image for text information; and

convert the bit-mapped representation of the text information into image text.

22. The product of claim 20 wherein the instructions to identify image text comprise instructions to:

search metadata information associated with the image for text describing the image.

23. The product of claim 22 wherein the metadata information is compatible with hypertext markup language (HTML).

24. The product of claim 20 wherein the instructions to generate the proximity factor for an image and a document keyword of a document keyword and image pair further comprise instructions to lexically analyze the image text associated with the image and the document keyword to determine the degree of correlation between the image and the document keyword.

25. The product of claim 20 wherein the instructions to generate the proximity factor for an image and a document keyword of a document keyword and image pair further comprise instructions to perform a phonetic comparison between the image text associated with the image and the document keyword to determine the degree of correlation between the image and the document keyword.

26. The product of claim 15 wherein the instructions to generate the proximity factor for an image and a document keyword of a document keyword and image pair further comprise instructions to:

identify the location of the image in the document;

measure the distance between the image in the document and the document keyword; and

determine the correlation between the document keyword and the image according to the distance between the document keyword and the image.