Methods and Systems for Content-Boundary Detection

• US 20100014774A1
• Filed: 07/17/2008
• Published: 01/21/2010
• Est. Priority Date: 07/17/2008
• Status: Active Grant

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Chen, Lawrence Shao-hsien, Dolan, John E.
• Granted Patent: US 9,547,799 B2
• Time in Patent Office: Days
• US Class Current: 382/266
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees
• CPC Class Codes: G06V 10/243 by compensating for image skew or non-uniform image deformations

Abstract

Aspects of the present invention are related to systems and methods for automatically determining the content boundaries in a digital image.

Claims

1. A method for content-boundary detection in a digital image, said method comprising:

a) determining the location of edges in a first image related to a digital image, thereby producing an edge map;

b) forming a first projection histogram of said edge map in a first projection direction;

c) forming a second projection histogram of said edge map in a second projection direction, wherein said second projection direction is normal to said first projection direction; and

d) determining a content boundary associated with said digital image using said first projection histogram and said second projection histogram.

2. A method as described in claim 1 further comprising:

a) receiving a skew parameter;

b) determining a skew vector associated with said skew parameter; and

c) wherein;

i) said first projection direction is related to said skew vector; and

ii) said second projection direction is related to the normal of said skew vector.

3. A method as described in claim 1, wherein said first image is a low-resolution representation of said digital image.

4. A method as described in claim 1, wherein said first image is a smoothed version of said digital image.

5. A method as described in claim 4, wherein said smoothed version of said digital image is formed by convolving said digital image with a Gaussian filter.

6. A method as described in claim 1, wherein said first image is a smoothed version of a low-resolution representation of said digital image.

7. A method as described in claim 1 further comprising clipping said digital image according to said content boundary.

8. A method as described in claim 1, wherein said determining the location of edges comprises:

a) determining a first gradient field of said first image in a first direction;

b) determining a second gradient field of said first image in a second direction;

c) computing a gradient magnitude from said first gradient field and said second gradient field; and

d) thresholding said gradient magnitude.

9. A method as described in claim 8, wherein:

a) said determining a first gradient field comprising convolving said first image with a first edge kernel; and

b) said determining a second gradient field comprises convolving said first image with a second edge kernel.

10. A method as described in claim 8, wherein said thresholding comprises a threshold based on the mean of said gradient magnitude and an adjustable rejection parameter associated with edge strength.

11. A method as described in claim 1, wherein said determining a content boundary associated with said digital image using said first projection histogram and said second projection histogram comprises:

a) determining a first coordinate in a first coordinate direction, wherein said first coordinate is associated with the first histogram bin having a non-zero count in said first projection histogram;

b) determining a second coordinate in said first coordinate direction, wherein said second coordinate is associated with the last histogram bin having a non-zero count in said first projection histogram;

c) determining a third coordinate in a second coordinate direction, wherein said third coordinate is associated with the first histogram bin having a non-zero count in said second projection histogram;

d) determining a fourth coordinate in said second coordinate direction, wherein said fourth coordinate is associated with the last histogram bin having a non-zero count in said second projection histogram; and

e) wherein said content boundary is a bounding rectangle described by the four vertices given by;

i) said first coordinate and said third coordinate;

ii) said first coordinate and said fourth coordinate;

iii) said second coordinate and said third coordinate; and

iv) said second coordinate and said fourth coordinate.

12. A method for content-boundary detection in a digital image, said method comprising:

a) partitioning a first image into a plurality of image tiles, said plurality of image tiles comprising a first tile and a second tile;

b) determining the location of edges in said first tile, thereby producing a first edge map;

c) forming a first first-tile projection histogram of said first edge map in a first projection direction;

d) forming a second first-tile projection histogram of said first edge map in a second projection direction, wherein said second projection direction is normal to said first projection direction;

e) determining a first-tile content boundary associated with said first tile using said first first-tile projection histogram and said second first-tile projection histogram;

f) determining the location of edges in said second tile, thereby producing a second edge map;

g) forming a first second-tile projection histogram of said second edge map in said first projection direction;

h) forming a second second-tile projection histogram of said second edge map in said second projection direction;

i) determining a second-tile content boundary associated with said second tile using said first second-tile projection histogram and said second second-tile projection histogram; and

j) determining an image-content boundary using said first-tile content boundary and said second-tile content boundary.

13. A method as described in claim 12 further comprising:

a) receiving a skew parameter;

b) determining a skew vector associated with said skew parameter; and

c) wherein;

i) said first projection direction is related to said skew vector; and

ii) said second projection direction is related to the normal of said skew vector.

14. A method as described in claim 12, wherein said first image tile and said second image tile are non-overlapping.

15. A method as described in claim 12, wherein said first image tile and said second image tile are overlapping.

16. A method as described in claim 12, wherein said first image is a low-resolution representation of a digital image.

17. A method as described in claim 12, wherein said first image is a smoothed version of said digital image.

18. A method as described in claim 12, wherein said first image is a smoothed version of a low-resolution representation of said digital image.

19. A method as described in claim 12 further comprising clipping said digital image according to said image-content boundary.

20. A method as described in claim 12, wherein said determining the location of edges in said first tile comprises:

a) determining a first gradient field of said first tile in a first direction;

b) determining a second gradient field of said first tile in a second direction;

c) computing a gradient magnitude from said first gradient field and said second gradient field; and

d) thresholding said gradient magnitude.

21. A method as described in claim 20, wherein:

a) said determining a first gradient field comprising convolving said first tile with a first edge kernel; and

b) said determining a second gradient field comprises convolving said first tile with a second edge kernel.

22. A method as described in claim 20, wherein said thresholding comprises a threshold based on the mean of said gradient magnitude and an adjustable rejection parameter associated with edge strength.

23. A method as described in claim 12, wherein said determining a first-tile content boundary using said first first-tile projection histogram and said second first-tile projection histogram comprises:

a) determining a first coordinate in a first coordinate direction, wherein said first coordinate is associated with the first histogram bin having a non-zero count in said first first-tile projection histogram;

b) determining a second coordinate in said first coordinate direction, wherein said second coordinate is associated with the last histogram bin having a non-zero count in said first first-tile projection histogram;

c) determining a third coordinate in a second coordinate direction, wherein said third coordinate is associated with the first histogram bin having a non-zero count in said second first-tile projection histogram; and

d) determining a fourth coordinate in said second coordinate direction, wherein said fourth coordinate is associated with the last histogram bin having a non-zero count in said second first-tile projection histogram.

24. A method as described in claim 12, wherein said determining an image-content boundary using said first-tile content boundary and said second-tile content boundary comprises:

a) comparing a first-tile first coordinate in a first coordinate direction, wherein said first-tile first coordinate is associated with the first histogram bin having a non-zero count in said first first-tile projection histogram, and a second-tile first coordinate in said first coordinate direction, wherein said second-tile first coordinate is associated with the first histogram bin having a non-zero count in said first second-tile projection histogram;

b) comparing a first-tile second coordinate in said first coordinate direction, wherein said first-tile second coordinate is associated with the last histogram bin having a non-zero count in said first first-tile projection histogram, and a second-tile second coordinate in said first coordinate direction, wherein said second-tile second coordinate is associated with the last histogram bin having a non-zero count in said first second-tile projection histogram;

c) comparing a first-tile third coordinate in a second coordinate direction, wherein said first-tile third coordinate is associated with the first histogram bin having a non-zero count in said second first-tile projection histogram, and a second-tile third coordinate in said second coordinate direction, wherein said second-tile third coordinate is associated with the first histogram bin having a non-zero count in said second second-tile projection histogram; and

d) comparing a first-tile fourth coordinate in said second coordinate direction, wherein said first-tile fourth coordinate is associated with the last histogram bin having a non-zero count in said second first-tile projection histogram, and a second-tile fourth coordinate in said second coordinate direction, wherein said second-tile fourth coordinate is associated with the last histogram bin having a non-zero count in said second second-tile projection histogram.

25. A system for content-boundary detection in a digital image, said system comprising:

a) an edge extractor for determining the location of edges in a first image related to a digital image, thereby producing an edge map;

b) a first projection histogram generator for forming a first projection histogram of said edge map in a first projection direction;

c) a second projection histogram generator for forming a second projection histogram of said edge map in a second projection direction, wherein said second projection direction is normal to said first projection direction; and

d) a boundary determiner for determining a content boundary associated with said digital image using said first projection histogram and said second projection histogram.

26. A system as described in claim 25 further comprising:

a) a skew parameter receiver for receiving a skew parameter; and

b) a skew vector determiner for determining a skew vector associated with said skew parameter.