Method for detecting color objects in digital images

• US 20040170318A1
• Filed: 02/28/2003
• Published: 09/02/2004
• Est. Priority Date: 02/28/2003
• Status: Active Grant

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Eastman Kodak Company
• Inventors: Luo, Jiebo, Crandall, David J.
• Granted Patent: US 7,263,220 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 10/758 Involving statistics of pixels or of feature values, e.g. histogram matching

Abstract

A method for detecting an object in a digital image including the steps of performing color quantization on a model image including the object and on a search image that potentially includes the object, generating a plurality of search windows, computing spatial-color joint probability functions of each model and search image, where the color co-occurrence edge histogram is chosen to be the spatial-color joint probability function, assessing the similarity of each search image to the model, and designating search windows as containing the target object.

Claims

1. A method of finding a color object in a digital image, comprising the steps of:

(a) obtaining a search image that potentially includes the color object;

(b) obtaining a model image including a model of the color object;

(c) computing a Spatial Color Joint Probability Function (SCJPF) for the model image, wherein a model image SCJPF is a distribution of colors as well as spatial relationships between such colors in the model image;

(d) generating a plurality of search windows each comprising a portion of the search image, with each portion being within a region of the image having a minimum predefined number of the colors present in the object model image;

(e) computing a SCJPF for each search window, wherein a search window SCJPF is a distribution of colors as well as spatial relationships between such colors in the search window;

(f) assessing a degree of similarity between the model image SCJPF and each of the search window SCJPFs; and

(g) designating search windows associated with search window SCJPFs having a degree of similarity to the model image SCJPF which exceeds a prescribed search threshold as potentially containing the object being sought.

2. The method as claimed in claim 1 further comprising the step of performing color quantization on both the model image and the search image, wherein the number of unique colors in the images is reduced to a set of pre-determined perceptually related color names.

3. The method as claimed in claim 2 wherein the color quantization step is further comprised of the steps of:

converting each pixel value in the model image and the search image to a suitable color space;

assigning each pixel a color name based on the location of its color value within the color space; and

assigning each pixel a quantized color value based on its assigned color name.

4. The method as claimed in claim 2 wherein the reduced set of pre-determined perceptually related color names includes human skin color.

5. The method as claimed in claim 2 wherein the step of performing color quantization further includes mapping the color of a pixel to more than one color name in the reduced set of pre-determined perceptually related color names.

6. The method as claimed in claim 1 wherein the steps (c) and (e) of computing a SCJPF comprises computing an edge SCJPF for the model image and each search window, wherein the edge SCJPF is computed by generating counts of every pair of color edge pixels whose pixels exhibit a prescribed pixel characteristic that fall within the same combination of said series of pixel characteristic ranges and which are separated by a distance falling within the same one of said series of distance ranges.

7. The method as claimed in claim 1 wherein the step (g) of designating search windows employs a similarity assessment that is performed by mathematical correlation of the model image SCJPF and each of the search window SCJPFs.

8. The method as claimed in claim 1 wherein the step (e) of computing a Spatial Color Joint Probability Function (SCJPF) for each search window further includes computing a first partial SCJPF for a part of the search window that does not overlap with a previously-visited search window, and adding the first partial SCJPF to a second partial SCJPF computed from the previously-visited search window.

9. The method as claimed in claim 1 further including a step of pre-screening the search image to identify regions that are more likely to contain the color object before generating a plurality of search windows in step (d), thereby eliminating regions that are less likely to contain the color object and that do not therefore warrant further processing.

10. A method of finding a color object in a digital image, comprising the steps of:

(a) obtaining a search image that potentially includes the color object;

(b) obtaining a model image including a model of the color object;

(c) performing color quantization on both the model image and the search image, wherein the number of unique colors in the images is reduced to a set of pre-determined perceptually related color names;

(d) computing a Spatial Color Joint Probability Function (SCJPF) for the model image, wherein a model image SCJPF is a distribution of colors as well as spatial relationships between such colors in the model image;

(e) generating a plurality of search windows each comprising a portion of the search image;

(f) computing a SCJPF for each search window, wherein a search window SCJPF is a distribution of colors as well as spatial relationships between such colors in the search window;

(g) assessing a degree of similarity between the model image SCJPF and each of the search window SCJPFs; and

(h) designating search windows associated with search window SCJPFs having a degree of similarity to the model image SCJPF which exceeds a prescribed search threshold as potentially containing the object being sought.

11. The method as claimed in claim 10 wherein each search window is within a region of the image having a minimum predefined number of the colors present in the object model image.

12. The method as claimed in claim 10 wherein the steps (d) and (f) of computing a SCJPF comprises computing an edge SCJPF for the model image and search window, wherein a search window SCJPF is computed by generating counts of every pair of color edge pixels whose pixels exhibit a prescribed pixel characteristic that fall within the same combination of said series of pixel characteristic ranges and which are separated by a distance falling within the same one of said series of distance ranges.

13. The method as claimed in claim 10 wherein the color quantization step (c) is further comprised of the steps of:

converting each pixel value in the model image and the search image to a suitable color space;

assigning each pixel a color name based on the location of its color value within the color space; and

assigning each pixel a quantized color value based on its assigned color name.

14. The method as claimed in claim 10 wherein the reduced set of pre-determined perceptually related color names includes human skin color.

15. The method as claimed in claim 10 wherein the step of performing color quantization further includes mapping the color of a pixel to more than one color name in the reduced set of pre-determined perceptually related color names.

16. The method as claimed in claim 10 wherein the step (h) of designating search windows employs a similarity assessment that is performed by mathematical correlation of the model image SCJPF and each of the search window SCJPFs.

17. The method as claimed in claim 10 wherein the step (f) of computing a Spatial Color Joint Probability Function (SCJPF) for each search window further includes computing a first partial SCJPF for a part of the search window that does not overlap with a previously-visited search window, and adding the first partial SCJPF to a second partial SCJPF computed from the previously-visited search window.

18. The method as claimed in claim 10 further including a step of pre-screening the search image to identify regions that are more likely to contain the color object before generating a plurality of search windows in step (d), thereby eliminating regions that are less likely to contain the color object and that do not therefore warrant further processing.

19. A method of finding a color object in a digital, comprising the steps of:

(a) obtaining a search image that potentially includes the color object;

(b) capturing a model image including a model of the color object;

(c) computing a Spatial Color Joint Probability Function (SCJPF) for the model image, wherein a model image SCJPF is a distribution of colors at color edges as well as spatial relationships between such colors in the model image, wherein a color edge is defined as a pixel whose color is different from its neighboring pixels according to a predetermined threshold;

(d) generating a plurality of search windows each comprising a portion of the search image;

(e) computing an edge SCJPF for each search window, wherein a search window SCJPF is a distribution of colors at color edges as well as spatial relationships between such colors in the search window;

(f) assessing a degree of similarity between the model image edge SCJPF and each of the search window edge SCJPFs; and

(g) designating search windows associated with search window edge SCJPFs having a degree of similarity to the model image edge SCJPF which exceeds a prescribed search threshold as potentially containing the object being sought.

20. The method as claimed in claim 19 further comprising the step of performing color quantization on both the model image and the search image, wherein the number of unique colors in the images is reduced to a set of pre-determined perceptually related color names.

21. The method as claimed in claim 20 wherein the color quantization step is further comprised of the steps of:

converting each pixel value in the model image and the search image to a suitable color space;

assigning each pixel a color name based on the location of its color value within the color space; and

assigning each pixel a quantized color value based on its assigned color name.

22. The method as claimed in claim 20 wherein the reduced set of pre-determined perceptually related color names includes human skin color.

23. The method as claimed in claim 20 wherein the step of performing color quantization further includes mapping the color of a pixel to more than one color name in the reduced set of pre-determined perceptually related color names.

24. The method as claimed in claim 19 wherein each search window is within a region of the image having a minimum predefined number of the colors present in the object model image.

25. The method as claimed in claim 19 wherein the step (g) of designating search windows employs a similarity assessment that is performed by mathematical correlation of the model image SCJPF and each of the search window SCJPFs.

26. The method as claimed in claim 19 wherein the step (e) of computing a Spatial Color Joint Probability Function (SCJPF) for each search window further includes computing a first partial SCJPF for a part of the search window that does not overlap with a previously-visited search window, and adding the first partial SCJPF to a second partial SCJPF computed from the previously-visited search window.

27. The method as claimed in claim 19 further including a step of pre-screening the search image to identify regions that are more likely to contain the color object before generating a plurality of search windows in step (d), thereby eliminating regions that are less likely to contain the color object and that do not therefore warrant further processing.

28. A method of finding a color object in a digital, comprising the following steps:

(a) obtaining a search image that potentially includes the color object;

(b) capturing a model image including a model of the color object;

(c) computing an edge Spatial Color Joint Probability Function (SCJPF) for the model image, wherein a model image edge SCJPF is a distribution of colors at color edges as well as spatial relationships between such colors in the model image, wherein a color edge is defined as a pixel whose color is different from its neighboring pixels according to a predetermined threshold;

(d) generating a plurality of search windows each comprising a portion of the search image;

(e) computing an edge SCJPF for each search window, wherein a search window SCJPF is a distribution of colors at color edges as well as spatial relationships between such colors in the model image;

(f) assessing a first degree of similarity between the model image edge SCJPF and each of the search window edge SCJPFs;

(g) computing a Spatial Color Joint Probability Function (SCJPF) for the model image, wherein a model image SCJPF is a distribution of colors as well as spatial relationships between such colors in the model image;

(h) computing a SCJPF for each search window, wherein a search window SCJPF is a distribution of colors as well as spatial relationships between such colors in the search window;

(i) assessing a second degree of similarity between the model image SCJPF and the search window SCJPF; and

(j) designating a search window associated with (1) search window edge SCJPFs having a first degree of similarity to the model image edge SCJPFs which exceeds a first prescribed search threshold and (2) a search window SCJPF having a second degree of similarity to a model image SCJPF which exceeds a second prescribed search threshold as potentially containing the object being sought.

29. The method as claimed in claim 28 further comprising the step of performing color quantization on both the model image and the search image, wherein the number of unique colors in the images is reduced to a set of pre-determined perceptually related color names.

30. The method as claimed in claim 29 wherein the color quantization step is further comprised of the steps of:

converting each pixel value in the model image and the search image to a suitable color space;

assigning each pixel a color name based on the location of its color value within the color space; and

assigning each pixel a quantized color value based on its assigned color name.

31. The method as claimed in claim 29 wherein the reduced set of predetermined perceptually related color names includes human skin color.

32. The method as claimed in claim 29 wherein the step of performing color quantization further includes mapping the color of a pixel to more than one color name in the reduced set of pre-determined perceptually related color names.

33. The method as claimed in claim 28 wherein each search window is within a region of the image having a minimum predefined number of the colors present in the object model image.

34. The method as claimed in claim 28 wherein the step (l) of designating search windows employs a similarity assessment that is performed by mathematical correlation of the model image SCJPF and each of the search window SCJPFs, and the model image color histogram and each of the search window color histograms.

35. The method as claimed in claim 28 wherein the step (e) of computing a Spatial Color Joint Probability Function (SCJPF) for each search window further includes computing a first partial SCJPF for a part of the search window that does not overlap with a previously-visited search window, and adding the first partial SCJPF to a second partial SCJPF computed from the previously-visited search window.

36. The method as claimed in claim 28 further including a step of pre-screening the search image to identify regions that are more likely to contain the color object before generating a plurality of search windows in step (d), thereby eliminating regions that are less likely to contain the color object and that do not therefore warrant further processing.