Method and computer program product for producing an image of a desired aspect ratio

1. A method for producing a new image of a desired aspect ratio from an original digital image, said method comprising the steps of:

(a) determining a cropping window of the desired aspect ratio and a predetermined size relative to the size of the original digital image;

(b) obtaining a main subject belief map including an array of belief values indicating the location and relative importance of subject matter in the original digital image;

(c) using the main subject belief map, determining a location of the cropping window in the original digital image that satisfies a predetermined set of criteria; and

(d) producing a cropped image of the desired aspect ratio.

2. The method as claimed in claim 1 , wherein the desired aspect ratio is selected from the group including a 3×5, 4×6, 5×7, and 8×10 aspect ratio.

3. The method as claimed in claim 1 , wherein the predetermined size of the cropping window is the largest size allowable by the original digital image.

4. The method as claimed in claim 1 , wherein the set of predetermined criteria include a maximum scene content index value, where a scene content index value is defined as the sum of the belief values within the cropping window.

5. The method as claimed in claim 1 , wherein the set of predetermined criteria include regions of highest belief values in their entirety.

6. The method as claimed in claim 1 , wherein the set of predetermined criteria include maintaining a predetermined amount of space between a top image border of the original digital image and regions of highest main subject belief values.

7. The method as claimed in claim 1 , wherein the set of predetermined criteria include retaining a predetermined amount of open space at a top image border of the original digital image.

8. The method as claimed in claim 1 , wherein the set of predetermined criteria include assigning a weight in response to a relative location of the cropping window to the center of the original digital image.

9. The method as claimed in claim 1 , wherein the step of obtaining a main subject belief map includes the steps of:

(i) extracting regions of homogenous properties from the original digital image;

(ii) extracting for each of the regions at least one structural saliency feature and at least one semantic saliency feature; and

(iii) integrating the structural saliency feature and the semantic saliency feature using a probabilistic reasoning engine to produce an estimate of a belief value that each region is the main subject.

10. The method as claimed in claim 9 , wherein step (ii) uses centrality as the structural saliency feature.

11. The method as claimed in claim 9 , wherein step (ii) uses borderness as the structural saliency feature.

12. The method as claimed in claim 9 , wherein step (ii) uses a presence of human skin tones as the semantic saliency feature.

13. The method as claimed in claim 9 , wherein step (ii) uses a presence of human faces as the semantic saliency feature.

14. The method as claimed in claim 9 , wherein step (iii) uses a Bayes network as the probabilistic reasoning engine.

15. The method as claimed in claim 4 , wherein the step of determining a location of the cropping window includes the steps of:

(i) computing an integral image from the main subject belief map;

(ii) computing the subject content index of a cropping window; and

(iii) selecting a location of the cropping window that produces a maximum subject content index value.

16. The method as claimed in claim 1 , wherein the step of determining a location of the cropping window further includes determining a series of all possible locations for the size of the cropping window for a user to choose from.

17. A computer program product for producing a new image of a desired aspect ratio from an original digital image comprising: a computer readable storage medium having a computer program stored thereon for performing the steps of:

(a) determining a cropping window of the desired aspect ratio and a predetermined size;

(b) obtaining a main subject belief map including an array of belief values indicating the location and relative importance of subject matter in the original digital image;

(c) using the main subject belief map, determining a location of the cropping window in the original digital image that satisfies a predetermined set of criteria; and

(d) producing a cropped image of the desired aspect ratio.

18. The computer program product as claimed in claim 17 wherein the steps (a) through (d) are performed by an on-line print fulfilling system for producing a print of a desired aspect ratio from a digital image.

19. The computer program product as claimed in claim 17 wherein the steps (a) through (d) are performed by a digital mini-lab photo finishing system for producing a print of a desired aspect ratio from a digital image.

20. The computer program product as claimed in claim 17 wherein the steps (a) through (d) are performed by an interactive stand-alone digital photo finishing system for producing a print of a desired aspect ratio from a digital image.

21. The computer program product as claimed in claim 17 wherein the steps (a) through (d) are performed by a wholesale digital photo finishing system for producing a print of a desired aspect ratio from a digital image.