Methods and systems for detecting regions in digital images

• US 20070206855A1
• Filed: 03/02/2006
• Published: 09/06/2007
• Est. Priority Date: 03/02/2006
• Status: Active Grant

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Campbell, Richard
• Granted Patent: US 7,889,932 B2
• Time in Patent Office: Days
• US Class Current: 382/171
• CPC Class Codes: G06V 10/507 Summing image-intensity values; Histogram projection analysis
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

Embodiments of the present invention comprise systems, methods and devices for detection of image regions of various content types using a masking condition and an entropy measure.

Claims

1. A method for calculating an entropy feature in a digital image comprising a plurality of pixels, said method comprising:

a) applying a masking condition to said digital image thereby identifying masked pixels that satisfy said masking condition; and

b) calculating an entropy measure wherein said masked pixels contribute less to said entropy measure than pixels not identified by said masking condition.

2. A method as described in claim 1 wherein said calculating excludes said masked pixels.

3. A method as described in claim 1 wherein said masking condition comprises a confidence measure.

4. A method as described in claim 3 wherein said contribution of said masked pixels is related to said confidence measure.

5. A method as described in claim 4 wherein said calculating comprises generating a histogram.

6. A method as described in claim 1 wherein said calculating comprises generating a histogram.

7. A method as described in claim 1 wherein said masking condition comprises edge strength.

8. A method as described in claim 3 wherein said masking condition comprises edge strength.

9. A system for calculating an entropy feature in a digital image, said system comprising:

a) an processor for applying a masking condition to said digital image thereby identifying masked pixels that satisfy said masking condition; and

b) a calculator for calculating an entropy measure wherein said masked pixels contribute less to said entropy measure than pixels not identified by said masking condition.

10. A system as described in claim 9 wherein said calculating excludes said masked pixels.

11. A system as described in claim 9 wherein said masking information comprises a confidence measure.

12. A system as described in claim 11 wherein said contribution of said masked pixels is related to said confidence measure.

13. A system as described in claim 12 wherein said calculator comprises a histogram generator.

14. A system as described in claim 9 wherein said calculator comprises a histogram generator.

15. A system as described in claim 14 wherein said histogram generator accumulates pixels from said digital image for which said masking condition is not met.

16. A system as described in claim 13 wherein said histogram generator accumulates said masked pixels based on said confidence measure.

17. A system as described in claim 9 wherein said masking condition comprises edge strength.

18. A system as described in claim 11 wherein said masking condition comprises edge strength.

19. A method for detecting a region in a digital image, said method comprising:

a) applying a masking condition to said digital image thereby identifying masked pixels that satisfy said masking condition;

b) calculating an entropy measure wherein said masked pixels contribute less to said entropy measure than pixels not identified by said masking condition; and

c) classifying a neighborhood of said digital image based on said entropy measure.

20. A method as described in claim 19 wherein said calculating excludes said masked pixels.