Color enhancement technique using skin color detection

• US 7,853,094 B2
• Filed: 11/28/2006
• Issued: 12/14/2010
• Est. Priority Date: 01/24/2006
• Status: Expired due to Fees

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Daly, Scott J., Pan, Hao
• Primary Examiner(s): Perungavoor; Sath V
• Assistant Examiner(s): Cunningham; Gregory F
• Application Number:
  US11/605,711
• Publication Number:
  US 20070172119A1
• Time in Patent Office: 1,477 Days
• Field of Search: None
• US Class Current: 382/254
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: H04N 1/62 Retouching, i.e. modification of isolated colours only or in isolated picture areas only
• CPC Class Codes: H04N 1/628 Memory colours, e.g. skin or sky

Abstract

A method for enhancing the color of an image to be displayed on a display includes receiving an image having a plurality of pixels where each of the pixels has a plurality of color components. The image is filtered using a spatial filter in such a manner that the lower frequency content of the image is enhanced in such a manner that the color gamut of the lower frequency content is increased. The filtered image is modified such that the higher frequency content of the image to obtain a modified image that includes the higher frequency content and the lower frequency content.

Claims

1. A method for enhancing the color of an image to be displayed on a display comprising:

(a) a processor receiving an image having a plurality of pixels where each of said pixels has a plurality of color components;

(b) a processor filtering said image with a spatial filter to define skin regions displaying a person'"'"'s skin, wherein said skin regions are enhanced such that the distribution of the colors in said skin regions is modified in a first manner, and wherein said spatial filter has a first component that associates pixels of said image with respective scores that each represent the likelihood that the pixel has a skin tone, and a second component that filters said respective scores;

(c) a processor filtering said image with a filter to enhance regions of said image other than said skin regions such that the distribution of the colors in said regions of said image other than said skin regions are modified in a second manner;

(d) whereby said image is modified to include said filtered regions of said image other than said skin regions and said filtered skin regions.

2. The method of claim 1 wherein said modified image is displayed on a display, where said display has a larger color gamut than said received image, wherein said filtering said image results in a compressing of the distribution of colors in said skin regions.

3. The method of claim 1 wherein the edge regions of said skin regions are filtered to create a graduated transition between said skin regions and said regions of said image other than said skin regions.

4. The method of claim 1 wherein said modified image is displayed on a display, where said display has substantially the same color gamut as said received image, wherein said modification distributes colors in said skin regions such that when rendered by said display the colors of said image other than said skin regions are increased in saturation, while the colors of said skin regions are not increased in saturation to the same extent as said colors of said image other than said skin regions.

5. The method of claim 1 wherein said skin regions are defined by a spatial low pass filter.

6. The method of claim 1 wherein said spatial filter is a sigma filter.

7. The method of claim 1 wherein said image is received from the output of a sigma filer filter.

8. The method of claim 1 wherein said spatial filter includes a region defined around a pixel of interest.

9. The method of claim 8 wherein said spatial filter determines pixels within said region that are sufficiently similar to said pixel of interest.

10. The method of claim 1 wherein said filtering includes a look-up table to further define said skin regions.

11. The method of claim 1 wherein said filtering includes a spatial characteristic that determines whether proximate pixels have skin-tones.

12. The method of claim 1 wherein said filtering includes a color space characteristic that determines if proximate pixels have skin-tones.

13. The method of claim 1 wherein said image is separated into a base image of low-frequency content and a residual image of high-frequency content, where said residual image is not filtered with said spatial filter and is not filtered with said filter.

14. The method of claim 13 wherein said lower frequency content is separated by edges.

15. The method of claim 13 wherein said higher frequency content includes high frequency details, noise, and artifacts.

16. The method of claim 1 wherein said filter includes a threshold.

17. The method of claim 16 wherein said threshold is based upon the content of said image.