Subjective and locatable color theme extraction for images

• US 8,041,111 B1
• Filed: 11/15/2007
• Issued: 10/18/2011
• Est. Priority Date: 10/15/2007
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Wilensky, Gregg D.
• Primary Examiner(s): Ahmed; Samir
• Assistant Examiner(s): Liu; Li
• Application Number:
  US11/985,532
• Time in Patent Office: 1,433 Days
• Field of Search: None
• US Class Current: 382/168
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: H04N 1/62 Retouching, i.e. modification of isolated colours only or in isolated picture areas only

Abstract

Systems, methods, and program products for subjective and locatable color theme extraction for images. Determining a color density for each of a plurality of colors in an image where each of the plurality of colors belongs to a color space, extracting one or more distinct theme colors from the plurality of colors based on qualitative parameters and the determined color densities, and mapping each extracted theme color to a color occurring in the image where the mapping is based on a color distance between the theme color and colors occurring in the image.

Claims

1. A computer-implemented method, comprising:

receiving one or more qualitative color theme parameters;

determining a color density for each of a plurality of colors in an image where each of the plurality of colors belongs to a color space;

extracting one or more distinct theme colors from the plurality of colors based on the qualitative parameters and the determined color densities; and

mapping each extracted theme color to a color occurring in the image where the mapping is based on a color distance between the theme color and colors occurring in the image.

2. The method of claim 1 where a qualitative color theme parameter is a degree of:

colorfulness, brightness, looseness, tightness, saturation, shadow suppression, cheerfulness, or drabness.

3. The method of claim 1 where each determined color density is a normalized logarithmic density weighted by the color theme parameters.

4. The method of claim 1 where extracting comprises:

selecting the theme colors so as to minimize a function that takes into account the determined color density of each theme color and color distances between all pairs of the theme colors.

5. The method of claim 4 where theme colors are attracted to image areas of high color density and repulsed from colors that are close in color distance to other theme colors.

6. The method of claim 4 where the measure of color distance is Euclidean distance in CIELAB color space.

7. The method of claim 1, further comprising:

determining a spatial location where each mapped theme color occurs in the image.

8. The method of claim 7, further comprising:

accepting input to change the determined spatial location for a first theme color to a new spatial location in the image; and

changing the first theme color to be the color corresponding to the new spatial location.

9. A computer program product, encoded on a non-transitory computer-readable medium, operable to cause data processing apparatus to perform operations comprising:

receiving one or more qualitative color theme parameters;

determining a color density for each of a plurality of colors in an image where each of the plurality of colors belongs to a color space;

extracting one or more distinct theme colors from the plurality of colors based on the qualitative parameters and the determined color densities; and

mapping each extracted theme color to a color occurring in the image where the mapping is based on a color distance between the theme color and colors occurring in the image.

10. The program product of claim 9 where a qualitative color theme parameter is a degree of:

colorfulness, brightness, looseness, tightness, saturation, shadow suppression, cheerfulness, or drabness.

11. The program product of claim 9 where each determined color density is a normalized logarithmic density weighted by the color theme parameters.

12. The program product of claim 9 where extracting comprises:

selecting the theme colors so as to minimize a function that takes into account the determined color density of each theme color and color distances between all pairs of the theme colors.

13. The program product of claim 12 where theme colors are attracted to image areas of high color density and repulsed from colors that are close in color distance to other theme colors.

14. The program product of claim 12 where the measure of color distance is Euclidean distance in CIELAB color space.

15. The program product of claim 9, further comprising:

determining a spatial location where each mapped theme color occurs in the image.

16. The program product of claim 15, further comprising:

accepting input to change the determined spatial location for a first theme color to a new spatial location in the image; and

changing the first theme color to be the color corresponding to the new spatial location.

17. A system comprising:

a user interface; and

one or more computers operable to interact with the user interface device and to perform the following operations;

receiving one or more qualitative color theme parameters;

determining a color density for each of a plurality of colors in an image where each of the plurality of colors belongs to a color space;

extracting one or more distinct theme colors from the plurality of colors based on the qualitative parameters and the determined color densities; and

mapping each extracted theme color to a color occurring in the image where the mapping is based on a color distance between the theme color and colors occurring in the image.

18. The system of claim 17, wherein the one or more computers comprise a server operable to interact with the user interface through a data communication network, and the user interface is operable to interact with the server as a client.

19. The system of claim 18, wherein the user interface device comprises a personal computer running a web browser.

20. The system of claim 17 where a qualitative color theme parameter is a degree of:

colorfulness, brightness, looseness, tightness, saturation, shadow suppression, cheerfulness, or drabness.

21. The system of claim 17 where each determined color density is a normalized logarithmic density weighted by the color theme parameters.

22. The system of claim 17 where extracting comprises:

selecting the theme colors so as to minimize a function that takes into account the determined color density of each theme color and color distances between all pairs of the theme colors.

23. The system of claim 22 where theme colors are attracted to image areas of high color density and repulsed from colors that are close in color distance to other theme colors.

24. The system of claim 22 where the measure of color distance is Euclidean distance in CIELAB color space.

25. The system of claim 17 where the computers are further operable to interact with the user interface device and to perform the following further operations:

determining a spatial location where each mapped theme color occurs in the image.