Method and an apparatus for visual summarization of documents

• US 7,519,906 B2
• Filed: 10/06/2004
• Issued: 04/14/2009
• Est. Priority Date: 05/31/2000
• Status: Active Grant

• Current Assignee: Ricoh Company Limited, Ricoh Corporation (Ricoh Company Limited)
• Original Assignee: Ricoh Company Limited, Ricoh Corporation (Ricoh Company Limited)
• Inventors: Lee, Dar-Shyang, Balabanovic, Marko
• Primary Examiner(s): RIES, LAURIE ANNE
• Application Number:
  US10/960,304
• Publication Number:
  US 20050160369A1
• Time in Patent Office: 1,651 Days
• Field of Search: 715/517, 715/838, 715/866, 715/513, 715/234, 715/243, 715/967
• US Class Current: 715/243
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: Y10S 707/99937 Sorting
• CPC Class Codes: Y10S 715/967 Visual or iconic programming

Abstract

A system and a method for visually summarizing a document comprising a display, a processor coupled to the display, and a memory coupled to the processor. Stored in the memory is a routine, which when executed by the processor, causes the processor to generate display data. The routine causes the processor to generate data through extracting at least one visual feature from a document having a plurality of pages, ranking the pages in a document, selecting a page for representing a document according to the visual feature, and displaying the selected page as display data.

Claims

1. A computer implemented method, comprising:

determining one or more constraints of a display area;

determining visual saliency of a plurality of page icons, the plurality of page icons representing pages of a document, based on at least one visual feature within the page icons, including determining a measure of the visual saliency of the plurality of page icons by at least a visual significance of said at least one visual feature and the presence of at least one predetermined visual feature that is based on a visual distinctiveness of the at least one predetermined visual feature in relation to a plurality of visual features;

determining, based on the one or more constraints of the display area and the one or more visual features within the page icons, whether one or more of the plurality of page icons are to be displayed in full and whether portions of one or more page icons are to be displayed partially obstructed by another page icon; and

displaying all of the plurality of page icons within the display area, the displayed plurality of page icons satisfying the one or more constraints of the display area and based on the visual saliency of the plurality of page icons.

2. The method of claim 1,wherein determining one or more constraints of the display area comprises determining a display area size, and wherein displayed size of the plurality of page icons is determined based on the size of the display area.

3. The method of claim 2, wherein a number of page icons that are overlapped is determined based on the size of the display area.

4. The method of claim 1, wherein determining one or more constraints of the display area comprises determining a shape of the display area, and wherein the plurality of page icons is displayed and arranged in a configuration within the display area based on the shape of the display area.

5. The method of claim 4, further comprising determining a number of page icons are to be overlapped based on the shape of the display area.

6. The method of claim 1, wherein the visual saliency of the at least one page icon is determined with respect to the remainder of the page icons that are overlapped.

7. The method of claim 1, wherein the presence of the at least one predetermined attractive visual feature increases an overall visual saliency of a page icon.

8. The method of claim 7, wherein an attractive visual feature is present in the page icon when the page icon includes at least one picture and text, if any.

9. The method of claim 7, wherein an attractive visual feature is present in the page icon when the page icon includes text above a predetermined size.

10. A tangible machine-readable storage medium having executable code to cause a machine to perform a method, the method comprising:

determining one or more constraints of a display area;

determining visual saliency of a plurality of page icons, the plurality of page icons representing pages of a document, based on at least one visual feature within the page icons, including determining a measure of the visual saliency of the plurality of page icons by at least a visual significance of said at least one visual feature and the presence of at least one predetermined visual feature that is based on a visual distinctiveness of the at least one predetermined visual feature in relation to a plurality of visual features;

determining, based on the one or more constraints of the display area and the one or more visual features within the page icons, whether one or more of the plurality of page icons are to be displayed in full and whether portions of one or more page icons are to be displayed partially obstructed by another page icon; and

displaying all of the plurality of page icons within the display area, the displayed plurality of page icons satisfying the one or more constraints of the display area and based on the visual saliency of the plurality of page icons.

11. The tangible machine-readable storage medium of claim 10, wherein determining one or more constraints of the display area comprises determining a display area size, and wherein displayed size of the plurality of page icons is determined based on the size of the display area.

12. The tangible machine-readable storage medium of claim 11, wherein a number of page icons that are overlapped is determined based on the size of the display area.

13. The tangible machine-readable storage medium of claim 10, wherein determining one or more constraints of the display area comprises determining a shape of the display area, and wherein the plurality of page icons is displayed and arranged in a configuration within the display area based on the shape of the display area.

14. The tangible machine-readable storage medium of claim 13, wherein the method further comprises determining a number of page icons are to be overlapped based on the shape of the display area.

15. The tangible machine-readable storage medium of claim 10, wherein the visual saliency of the at least one page icon is determined with respect to the remainder of the page icons that are overlapped.

16. A data processing system, comprising:

a processor; and

a memory coupled to the processor to store instructions, when executed from the memory, cause the processor to

determine one or more constraints of a display area,

determine visual saliency of a plurality of page icons, the plurality of page icons representing pages of a document, based on at least one visual feature within the page icons, including determining a measure of the visual saliency of the plurality of page icons by at least a visual significance of said at least one visual feature and the presence of at least one predetermined visual feature that is based on a visual distinctiveness of the at least one predetermined visual feature in relation to a plurality of visual features,

determine, based on the one or more constraints of the display area and the one or more visual features within the page icons, whether one or more of the plurality of page icons are to be displayed in full and whether portions of one or more page icons are to be displayed partially obstructed by another page icon, and

display all of the plurality of page icons within the display area, the displayed plurality of page icons satisfying the one or more constraints of the display area and based on the visual saliency of the plurality of page icons.

17. An apparatus, comprising:

means for determining one or more constraints of a display area;

means for determining visual saliency of a plurality of page icons, the plurality of page icons representing pages of a document, based on at least one visual feature within the page icons, including determining a measure of the visual saliency of the plurality of page icons by at least a visual significance of said at least one visual feature and the presence of at least one predetermined visual feature that is based on a visual distinctiveness of the at least one predetermined visual feature in relation to a plurality of visual features;

means for determining, based on the one or more constraints of the display area and the one or more visual features within the page icons, whether one or more of the plurality of page icons are to be displayed in full and whether portions of one or more page icons are to be displayed partially obstructed by another page icon; and

means for displaying all of the plurality of page icons within the display area, the displayed plurality of page icons satisfying the one or more constraints of the display area and based on the visual saliency of the plurality of page icons.

18. A computer implemented method, comprising:

determining one or more constraints of a display area;

determining visual saliency of one or more of a plurality of page icons, the plurality of page icons representing pages of a document, based on at least one visual feature of the document, including determining a measure of the visual saliency of the one or more of the plurality of page icons by at least a visual significance of said at least one visual feature and the presence of at least one predetermined attractive visual feature, wherein the presence of the at least one predetermined attractive visual feature increases an overall visual saliency of a page icon and an attractive visual feature is a visual feature that has been psychologically determined as being visually significant from among a plurality of visual features;

determining, based on the one or more constraints of the display area and the one or more visual features of the document, whether one or more of the plurality of page icons are to be displayed in full and whether portions of one or more page icons are to be displayed partially obstructed by another page icon; and

displaying the plurality of page icons within the display area, the displayed plurality of page icons satisfying the one or more constraints of the display area and based on the visual saliency of the plurality of page icons.