Method and system for enhancing portrait images that are processed in a batch mode

• US 7,636,485 B2
• Filed: 06/07/2006
• Issued: 12/22/2009
• Est. Priority Date: 02/28/2003
• Status: Expired due to Fees

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Eastman Kodak Company
• Inventors: Simon, Richard A., Matraszek, Tomasz
• Primary Examiner(s): Carter; Aaron W
• Application Number:
  US11/448,507
• Publication Number:
  US 20060228039A1
• Time in Patent Office: 1,294 Days
• Field of Search: 382/118, 382254-275, 348606-624
• US Class Current: 382/254
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06V 40/162 using pixel segmentation or colour matching
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/178 estimating age from face image; using age information for improving recognition
• CPC Class Codes: H04N 1/622 with simulation on a subsidiary picture reproducer
• CPC Class Codes: H04N 1/628 Memory colours, e.g. skin or sky

Abstract

A batch processing method for enhancing an appearance of a face located in a digital image, where the image is one of a large number of images that are being processed through a batch process, comprises the steps of: (a) providing a script file that identifies one or more original digital images that have been selected for enhancement, wherein the script file includes an instruction for the location of each original digital image; (b) using the instructions in the script file, acquiring an original digital image containing one or more faces; (c) detecting a location of facial feature points in the one or more faces, said facial feature points including points identifying salient features including one or more of skin, eyes, eyebrows, nose, mouth, and hair; (d) using the location of the facial feature points to segment the face into different regions, said different regions including one or more of skin, eyes, eyebrows, nose, mouth, neck and hair regions; (e) determining one or more facially relevant characteristics of the different regions; (f) based on the facially relevant characteristics of the different regions, selecting one or more enhancement filters each customized especially for a particular region and selecting the default parameters for the enhancement filters; (g) executing the enhancement filters on the particular regions, thereby producing an enhanced digital image from the original digital image; (h) storing the enhanced digital image; and (i) generating an output script file having instructions that indicate one or more operations in one or more of the steps (c)-(f) that have been performed on the enhanced digital image.

Claims

1. A method for enhancing the appearance of teeth and eyes in a face appearing in a digital image, while balancing their color and uniformity, said method comprising the steps of:

acquiring an input digital image having pixel values representative of teeth and eye regions of a face contained in the image from a digital image source;

determining a preferred color for the teeth and eye regions, the preferred color for the teeth and eye regions being difference from the color of the teeth and eye regions in the input image;

calculating a difference between each pixel value of the input digital image and a mean color value determined from the pixel values of the input digital image with a digital processing unit;

providing an enhanced digital image of the teeth and eyes by combining;

a) a scaled combination of said difference; and

b) the preferred color for the teeth and eye regions with the a digital processing unit, whereby the mean and variance of the color distributions of the pixels of the teeth and eyes in the enhanced digital image are shifted from the input image.

2. The method as claimed in claim 1 wherein the pixels are provided in CIELAB space comprising in part a luminance color vector, and the luminance color vector of the preferred color is chosen such that it is greater than the luminance color vector of the mean color.

3. The method as claimed in claim 1 wherein a color saturation of the preferred color is greater than the color saturation of the mean color.

4. The method as claimed in claim 1 wherein, to equalize the whites of the two eyes, either a same preferred color is used for both eyes or a color difference between the preferred colors of each eye is smaller than the color difference between the mean color for each eye.

5. A method for modifying colors of facial features in an input digital image having a plurality of pixels, each said pixel having a respective pixel value, said method comprising the steps of:

detecting one or more facial regions of the input digital image with a digital processing unit;

determining a mean color value of said one or more facial regions of the input digital image with the digital processing unit;

calculating a difference between each of the pixel values and said mean color value with the digital processing unit; and

computing a scaled combination of each of said differences and a predetermined preferred color of said one or more facial regions with the digital processing unit.

6. The method of claim 5 wherein said computing step shifts a mean and variance of a color distribution of the pixels of said one or more regions.

7. The method of claim 5 wherein said detecting further comprises locating facial feature points on a face in the digital image and segmenting said face using said facial feature points to provide said one or more facial regions.

8. The method of claim 5 wherein said preferred color varies spatially in said one or more facial regions.

9. The method of claim 5 wherein said one or more facial regions is one of:

a teeth region, an eye region, and a skin region.

10. The method of claim 5 wherein said one or more facial regions is a teeth region and a vector of said preferred colors is less color saturated than a vector of said color differences.

11. The method of claim 10 wherein said one or more facial regions is a teeth region and a vector of said preferred colors has greater luminance than a vector of said color differences.

12. The method of claim 5 wherein said one or more facial regions is a teeth region and a vector of said preferred colors has greater luminance than a vector of said color differences.

13. The method of claim 5 wherein said one or more facial regions are a pair of eye regions.

14. The method of claim 5 wherein said one or more facial regions are a pair of eye regions and a teeth region.

15. A computer storage medium having instructions stored therein for causing a computer to perform the method of claim 5.

16. A system for modifying colors of facial features in an input digital image having a plurality of pixels, each said pixel having a respective pixel value, said system comprising:

means for detecting one or more facial regions of the input digital image;

means for determining a mean color value of said one or more facial regions of the input digital image;

means for calculating a difference between each of the pixel values of the input digital image and said mean color value;

means for computing a scaled combination of each of said differences and a predetermined preferred color of said one or more facial regions and generating an enhanced digital image there from.