Hybrid Approach for Face Detection Using Skin Color Based Segmentation and Edge Detection

Abstract: In this paper, we propose a technique to efficiently detect human face in color images with varying illumination conditions. The strategy consists of modeling the distribution of skin colors gaussian fitted skin color model and segmenting the image into skin and non-skin parts, using threshold values that are computed automatically by an adaptive technique. Here we show that a mixture model of gaussians can provide a robust representation of the human skin color to accommodate with a lot of color variations. Using images taken from the internet, containing persons with various skin-color types in different illumination conditions, experimental results show that the proposed method can cope with a various range of illumination situations and complex backgrounds,where skin color based segmentation can segment the skin regions of human face and separated the non-skin regions and after that using edge detection operators(canny and prewitt) , which detect the face regions while reducing the noise around that region. In this way this hybrid approach provide us better system to detect the face region.

Keywords: Image segmentation, edge detection, segmentation, face detection, skin color, canny, prewitt