Color image processing method

• US 20030198380A1
• Filed: 06/05/2003
• Published: 10/23/2003
• Est. Priority Date: 05/17/1999
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd., Univeristy of Calif.
• Original Assignee: SAMSUNG ELECTRONICS CO., LTD.., UNIVERSITY OF , CALIF. AT SANTA BARBARA
• Inventors: Shin, Hyun-Doo, Deng, Yining, Choi, Yang-Lim, Manjunath, B.S.
• Granted Patent: US 7,245,762 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: H04N 1/644 using a reduced set of representative colours, e.g. each representing a particular range in a colour space
• CPC Class Codes: H04N 21/426 Internal components of the client ; Characteristics thereof H04N5/44 takes precedence

Abstract

A color image processing method is provided. The color image processing method includes the step of: (a) indexing a color image by assigning representative colors of an image to a color space divided into a plurality of regions. The color image processing method may be applied to object-based image processing such as MPEG-7, and fast search and retrieval of multimedia content can be made.

Claims

1. A color image processing method for indexing an image, comprising the step of (a) indexing a color image by assigning representative colors of an image to a color space divided into a plurality of regions.

2. The color image processing method according to claim 1, further comprising the step of (pa-1) obtaining the representative colors of the image and their ratio.

3. The color image processing method according to claim 2, wherein the ratio is a percentage.

4. The color image processing method according to claim 2 or claim 3, further comprising the step of (b) storing a region identifier expressing the representative colors, their ratio, and serial numbers of an image and a region in a database as data.

5. The color image processing method according to one of claims 1 through 3, wherein the image is one region selected from divided regions.

6. The color image processing method according to claim 4, wherein the image is one region selected from divided regions.

7. The color image processing method according to one of claims 1 through 3, wherein the color space is a three-dimensional color space.

8. The color image processing method according to claim 4, wherein the color space is a three-dimensional color space.

9. The color image processing method according to claim 5, wherein the color space is a three-dimensional color space.

10. The color image processing method according to claim 6, wherein the color space is a three-dimensional color space.

11. A color image processing method for indexing an image, comprising the steps of:

(a-1) obtaining a feature vector F expressed as an i-th representative color c_i and as its ratio p_i where N is a number of representative colors in the divided regions of an image, and i is an integer between 1 and N;

F={{c_i, p_i}, i=1, . . . , N};

(a-2) indexing the image by assigning the representative colors to lattice points of a 3-D color space divided into a plurality of regions; and

(a-3) storing indexed results in a database having the form of a separate table.

12. The color image processing method according to claim 11, wherein the ratio is a percentage.

13. The color image processing method according to claim 11 or claim 12, wherein the indexed results include a region identifier expressing the representative colors, their ratio, and serial numbers of an image and a region.

14. The color image processing method according to claim 11 or claim 12, wherein the image is one region selected from divided regions.

15. The color image processing method according to claim 13, wherein the image is one region selected from divided regions.

16. The color image processing method according to claim 11 or claim 12, wherein the color space is a three-dimensional color space.

17. The color image processing method according to claim 13, wherein the color space is a three-dimensional color space.

18. The color image processing method according to claim 14, wherein the color space is a three-dimensional color space.

19. The color image processing method according to claim 15, wherein the color space is a three-dimensional color space.

20. A medium for storing a program performing a color image processing method for indexing an image, said medium including computer readable program code means for:

(a-1) obtaining a feature vector F expressed as an i-th representative color c_i and as its percentage p_i when N is a number of representative colors in the divided regions of an image, and i is an integer between 1 and N;

F={{c_i, p_i}, i=1, . . . , N};

(a-2) indexing the image by assigning the representative colors to lattice points of a 3-D color space divided into a plurality of regions; and

(a-3) storing indexed results in a database having the form of a separate table.

21. The medium according to claim 20, wherein the indexed results include a region identifier expressing the representative colors, their ratio, and serial numbers of an image and a region.

22. A color image searching method for searching an image in a database based on a color feature of a query image, comprising the step of (a) performing a search based on representative colors of a query image and their ratio in the database indexed by assigning representative colors of a database image to a color space divided into a plurality of regions.

23. The color image searching method according to claim 22, wherein the color space is a three-dimensional color space.

24. The color image searching method according to claim 22, wherein step (a) comprises the steps of:

(a-1) obtaining representative colors of a given query image and their ratio;

(a-2) selecting a region corresponding to the representative colors obtained in the step (a-1) in a color space divided into a plurality of regions;

(a-3) selecting a data group indexed into the selected region from a database; and

(a-4) identifying matched data in which the difference in the ratio of the representative colors of the query image is less than a predetermined threshold value in the selected data group.

25. The color image searching method according to claim 24, wherein step (a) further comprises the steps of:

(a-5) obtaining the sum of the ratio of same regions from the identified data; and

(a-6) determining the region in which the difference between the sum of the obtained ratio and the sum of the ratio to the query image is less than a predetermined threshold value as a searched image.

26. The color image searching method according to claim 23, wherein step (a) comprises the steps of:

(a-1) obtaining representative colors of a given query image and their ratio;

(a-2) selecting a region corresponding to the representative colors obtained in the step (a-1) in a color space divided into a plurality of regions;

(a-3) selecting a data group indexed into the selected region from a database; and

(a-4) identifying matched data in which the difference in the ratio of the representative colors of the query image is less than a predetermined threshold value in the selected data group.

27. The color image searching method according to claim 26, wherein step (a) further comprises the steps of:

(a-5) obtaining the sum of the ratio of same regions from the identified matched data; and

(a-6) determining the region in which the difference between the sum of the obtained ratio and the sum of the ratio of the query image is less than a predetermined threshold value as a searched image.

28. The color image searching method according to claim 24 or claim 25, further comprising the step of performing the steps in a color space with respect to neighboring peripheral regions in the case where there are no regions determined as the searched image.

29. The color image searching method according to one of claims 22 through 27, wherein the ratio is a percentage.

30. The color image searching method according to claim 28, wherein the ratio is a percentage.

31. The color image searching method according to one of claims 22 through 27, wherein the query image is one region of the image divided into a plurality of regions, and the searched image is one region of the database image divided into a plurality of regions.

32. The color image searching method according to claim 28, wherein the query image is one region of the image divided into a plurality of regions, and the searched image is one region of the database image divided into a plurality of regions.

33. The color image searching method according to claim 29, wherein the query image is one region of the image divided into a plurality of regions, and the searched image is one region of the database image divided into a plurality of regions.

34. The color image searching method according to claim 30, wherein the query image is one region of the image divided into a plurality of regions, and the searched image is one region of the database image divided into a plurality of regions.

35. A color image searching method for searching an image in a database based on a color feature of a query image, comprising the steps of:

(a-1) obtaining representative colors of given query regions and their percentages;

(a-2) selecting a lattice point corresponding to the representative colors obtained in step (a-1) in a three-dimensional color space divided into a plurality of lattices;

(a-3) selecting a data group corresponding to the selected lattice point from the database in which a region identifier expressing representative colors of data images, their ratio, and serial numbers of an image and a region is stored as data; and

(a-4) identifying matched data in which the difference in the percentages of the representative colors of the query regions is less than a predetermined threshold value in the selected data group.

36. The color image searching method according to claim 35, further comprising the steps of:

(a-5) obtaining the sum of percentages of same regions from the identified matched data; and

(a-6) determining the region in which the difference between the sum of the obtained percentages and the sum of the percentages of the query regions is less than a predetermined threshold value as a searched image.

37. The color image searching method according to claim 36, further comprising the step of performing the steps in a color space with respect to neighboring peripheral lattice points in the case where there are no regions determined as the searched image.

38. A medium for storing a program performing a color image searching method, said medium including computer readable program code means for:

(a-1) obtaining representative colors of given query regions and their percentages;

(a-2) selecting a lattice point corresponding to the representative colors obtained in step (a-1) in a three-dimensional color space divided into a plurality of lattices;

(a-3) selecting a data group corresponding to the selected lattice point from the database in which a region identifier expressing representative colors of data images, their ratio, and serial numbers of an image and a region is stored as data; and

(a-4) identifying matched data in which the difference in the percentages of the representative colors of the query regions is less than a predetermined threshold value in the selected data group.

39. The medium according to claim 38, further comprising computer-readable program code means for:

(a-5) obtaining the sum of percentages of same regions from the identified data; and

(a-6) determining the region in which the difference between the sum of the obtained percentage and the sum of the percentages of the query regions is less than a predetermined threshold value as a searched image.

40. The medium according to claim 39, further comprising computer-readable program code means for performing said method in a color space with respect to neighboring peripheral lattice points in the case where there are no regions determined as the searched image.