Method and system for enhancing portrait images that are processed in a batch mode
View Patent ↗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.
1. An automatic retouching method for enhancing an appearance of a face located in a digital image, wherein said face has hair in a skin region thereof, said method comprising the steps of:
(a) acquiring a digital image containing one or more faces;
(b) detecting a location of facial feature points in the one or more faces, including special feature points that are useful for identifying the location of a facial hair region;
(c) defining a bounding box for the facial hair region by utilizing the feature points;
(d) generating a plurality of feature probability maps within the bounding box;
(e) combining the feature probability maps to generate a combined feature probability map for the facial hair region; and
(f) based on the combined feature probability map for the facial hair region, using an enhancement filter to enhance at least the texture or the skin tone of the facial hair region while masking off the facial hair, thereby producing an enhanced digital image from the digital image.
2. The method as claimed in claim 1 wherein the special feature points are eye locations and hairline and the hair is in a forehead area.
3. The method as claimed in claim 1 wherein the hair in a skin region comprises at least one of hair overlapping a forehead region and facial hair such as a moustache or beard.
4. The method as claimed in claim 1 wherein the feature probability maps include texture information and color information.
5. The method as claimed in claim 1 wherein the step of generating a plurality of feature probability maps comprises using a plurality of directional edge detectors to generate the maps.
6. The method as claimed in claim 1 wherein a feature probability map for hair texture is generated by the steps of:
calculating a vertical edge gradient;
generating a connected component map for all vertical edge gradients greater than a specified threshold;
calculating a normalized connected component density map from the connected component map; and
thresholding the normalized connected component density map to obtain a hair texture probability map.
7. A computer storage medium having instructions stored therein for causing a computer to perform the method of claim 1 .
8. An automatic retouching method for enhancing an appearance of a face located in a digital image, wherein said face has hair in a skin region thereof, said method comprising the steps of:
detecting facial feature points in the face;
defining a facial hair region bounding box using said feature points;
generating a plurality of feature probability maps within said bounding box;
combining said feature probability maps to generate a combined facial hair region feature probability map; and
using an enhancement filter based on said combined feature probability map, said enhancement filter enhancing at least one of texture and skin tone in the facial hair region bounding box while masking off facial hair.
9. The method of claim 8 wherein said facial feature points are eye locations and hairline.
10. The method of claim 8 wherein the feature probability maps include texture information and color information.
11. The method of claim 8 wherein said generating further comprises using a plurality of directional edge detectors.
12. The method of claim 8 wherein said generating further comprises:
calculating vertical edge gradients;
generating a connected component map for ones of said vertical edge gradients greater than a specified threshold;
calculating a normalized connected component density map from said connected component map; and
thresholding said normalized connected component density map to obtain a hair texture probability map.
13. A computer storage medium having instructions stored therein for causing a computer to perform the method of claim 8 .
14. An automatic retouching system for enhancing an appearance of a face located in a digital image, wherein said face has hair in a skin region thereof, said system comprising:
means for detecting facial feature points in the face;
means for defining a facial hair region bounding box using said feature points;
means for generating a plurality of feature probability maps within said bounding box;
means for combining said feature probability maps to generate a combined facial hair region feature probability map; and
means for using an enhancement filter based on said combined feature probability map, said enhancement filter enhancing at least one of texture and skin tone in the facial hair region bounding box while masking off facial hair.
15. The system of claim 14 wherein said facial feature points are eye locations and hairline.
16. The system of claim 14 wherein the feature probability maps include texture information and color information.
17. The system of claim 14 wherein said means for generating further comprises means for using a plurality of directional edge detectors.
18. The system of claim 14 wherein said means for generating further comprises:
means for calculating vertical edge gradients;
means for generating a connected component map for ones of said vertical edge gradients greater than a specified threshold;
means for calculating a normalized connected component density map from said connected component map; and
means for thresholding said normalized connected component density map to obtain a hair texture probability map.