Security

Face Detection by Skin Color and Feature Extractions

Date Added: May 2011
Format: PDF

In this paper a method is introduced that detects human faces in color images by first separating skin regions from non-skin regions and then locating faces within skin regions. A chroma chart is prepared that shows likelihoods of different colors representing the skin. Using the chroma chart, a color image is transformed into a gray scale image such that gray value at each pixel shows the likelihood value of the pixel representing the skin. This gray scale image is then converted into binary image with appropriate threshold to show skin and non-skin region. Skin regions having area less than half of the average face area is dropped. Then to identify the faces among the skin region, the authors inspect various features of these identified images.