Automatically producing an image of a portion of a photographic image

• US 20020114535A1
• Filed: 12/14/2000
• Published: 08/22/2002
• Est. Priority Date: 12/14/2000
• Status: Active Grant

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Eastman Kodak Company
• Inventors: Luo, Jiebo
• Granted Patent: US 6,654,507 B2
• Time in Patent Office: Days
• US Class Current: 382/282
• CPC Class Codes: G06T 7/66 of image moments or centre of gravity
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: H04N 1/3875 combined with enlarging or reducing enlarging or reducing per se H04N1/393

Abstract

A method of producing an image of at least a portion of a digital image, the digital image comprising pixels, comprising the steps of:

a) computing a belief map of the digital image, by using the pixels of the digital image to determine a series of features, and using such features to assign the probability of the location of a main subject of the digital image in the belief map;

b) determining a crop window having a shape and a zoom factor, the shape and zoom factor determining a size of the crop window; and

c) cropping the digital image to include a portion of the image of high subject content in response to the belief map and the crop window.

Claims

1. A method of producing an image of at least a portion of a digital image, the digital image comprising the steps of:

a) providing a digital image having pixels;

b) computing a belief map of the digital image, by using the pixels of the digital image to determine a series of features, and using such features to assign the probability of the location of a main subject of the digital image in the belief map;

c) determining a crop window having a shape and a zoom factor, the shape and zoom factor determining a size of the crop window; and

d) cropping the digital image to include a portion of the image of high subject content in response to the belief map and the crop window.

2. The method of claim 1 wherein step c) further comprises the steps of:

i) computing a weighted center-of-mass of the belief map, weighted by the belief values of the belief map;

ii) computing weighted central moments of the belief map, relative to the center-of-mass and weighted by a weighting function of each belief value of the belief map;

iii) computing an effective rectangular bounding box according to the central moments; and

iv) determining a crop window having a shape and a zoom factor, the shape and zoom factor determining a size of the crop window

3. The method of claim 1 wherein step d) further comprises the steps of:

i) selecting an initial position of the crop window at a location which includes the center of mass;

ii) using the belief values corresponding to the crop window to select the position of the crop window to include a portion of the image of high subject content in response to the belief map; and

iii) cropping the digital image according to the position of the crop window.

4. The method of claim 2 wherein step d) further comprises the steps of:

i) selecting a crop window of a rectangular shape and of an identical aspect ratio to the (uncropped) digital image; and

ii) selecting a zoom factor to determine the size of the crop window such that it encompasses the effective bounding box.

5. The method of claim 2 wherein the weighting function in step b) is a linear weighting function.

6. The method of claim 2 wherein the weighting function in step b) is a constant function.

7. The method of claim 3 wherein step b) further comprises the steps of:

i) calculating a subject content index for the crop window derived from the belief values;

ii) following a positioning procedure of repeating step i) for at least two positions of the crop window; and

iii) using the subject content index values to select the crop window position.

8. The method of claim 1 wherein the crop window is completely within the digital image.

9. The method of claim 2 wherein step b) further comprises the step of performing a clustering of the belief map to identify at least a cluster of highest belief values corresponding to main subject, a cluster of intermediate belief values corresponding to secondary subjects, and a cluster of lowest belief values corresponding to the background.

10. The method of claim 9 wherein said clustering includes setting said background portions to a zero belief value.

11. The method of claim 5 further comprising positioning said crop window such that the subject content index of said crop window is at an optimum.

12. The method of claim 3 further comprising positioning said crop window such that said crop window includes all of said main subject cluster.

13. The method of claim 12 further comprising positioning said crop window to include a buffer around said main subject cluster.

14. A computer storage product having at least one computer storage medium having instructions stored therein causing one or more computers to perform the method of claim 1.

16. The method of claim 15 wherein step c) further comprises the steps of:

i) computing a weighted center-of-mass of the belief map, weighted by the belief values of the belief map;

ii) computing weighted central moments of the belief map, relative to the center-of-mass and weighted by a weighting function of each belief value of the belief map;

iii) computing an effective rectangular bounding box according to the central moments; and

iv) determining a crop window having a shape and a zoom factor, the shape and zoom factor determining a size of the crop window.

17. The method of claim 15 wherein step d) further comprises the steps of:

i) selecting an initial position of the crop window at a location which includes the center of mass;

ii) using the belief values corresponding to the crop window to select the position of the crop window to include a portion of the image of high subject content in response to the belief map; and

iii) cropping the digital image according to the position of the crop window.

18. The method of claim 16 wherein step d) further comprises the steps of:

i) selecting a crop window of a rectangular shape and of an identical aspect ratio to the (uncropped) digital image; and

ii) selecting a zoom factor to determine the size of the crop window such that it encompasses the effective bounding box.

19. The method of claim 16 wherein the weighting function in step b) is a linear weighting function.

20. The method of claim 16 wherein the weighting function in step b) is a constant function.

21. The method of claim 17 wherein step b) further comprises the steps of:

i) calculating a subject content index for the crop window derived from the belief values;

ii) following a positioning procedure of repeating step i) for at least two positions of the crop window; and

iii) using the subject content index values to select the crop window position.

22. The method of claim 15 wherein the crop window is completely within the digital image.

23. The method of claim 16 wherein step b) further comprises the step of performing a clustering of the belief map to identify at least a cluster of highest belief values corresponding to main subject, a cluster of intermediate belief values corresponding to secondary subjects, and a cluster of lowest belief values corresponding to the background.

24. The method of claim 23 wherein said clustering includes setting said background portions to a zero belief value.

25. The method of claim 19 further comprising positioning said crop window such that the subject content index of said crop window is at an optimum.

26. The method of claim 17 further comprising positioning said crop window such that said crop window includes all of said main subject cluster.

27. The method of claim 26 further comprising positioning said crop window to include a buffer around said main subject cluster.

28. A computer storage product having at least one computer storage medium having instructions stored therein causing one or more computers to perform the method of claim 1.

15. A method of producing an image of a portion of at least a portion of a photographic image onto a photographic receiver, comprising the steps of:

a) receiving a digital image corresponding to the photographic image, the digital image comprising pixels;

b) computing a belief map of the digital image, by using the pixels of the digital image to determine a series of features, and using such features to assign the probability of the location of a main subject of the digital image in the belief map;

c) determining a crop window having a shape and a zoom factor, the shape and zoom factor determining a size of the crop window; and

d) locating the relative optical position of a photographic image, a lens assembly, and a photographic receiver in response to the belief map and illuminating a portion of the photographic image of high subject content to produce an image of such portion onto the photographic receiver.