Color Images Based Face Detection Using Skin Likelihood Model and Morphological Operations

Human face detection has become a major field of interest in current research because there is no deterministic algorithm to find face(s) in a given image. Further the algorithms that exist are very much specific to the kind of images they would take as input and detect faces. The problem is to detect faces in the given, colored group photograph. This paper proposes a novel technique for detecting faces in color images using skin likely-hood model , skin Segmentation, Morphological operation and Template matching. Color images with skin color in the chromatic and pure color space YCrCb, which separates luminance and chrominance components. A Gaussian probability density is estimated from skin samples, collected from different ethnic groups, via the maximum-likelihood criterion. Adaptive thresholding for segmentation to localize the faces within the detected skin regions. Then, mathematical morphological operators are used to remove noisy regions and fill holes in the skin-color region, so we can extract candidate human face regions. Experimental results on a large photo data set have demonstrated that the proposed model is able to achieve good detection success rates of varying orientations, skin color and background environment. These system is achieve high detection accuracy, high detection speed and reduce the false detecting rate. Keywords— Face detection, Skin Segmentation, SkinColor model, Skin likelihood, Morphological operation, Temaplate Matching