This paper presents a new human skin color model in YCbCr color space and its application to human face detection. Skin colors are modeled by a set of three Gaussian clusters, each of which is characterized by a centroid and a covariance matrix. The centroids and Covariance matrices are estimated from large set of training samples after a k-means clustering process. Pixels in a color input image can be classified into skin or nonskin based on the Mahalanobis distances to the three clusters. Efficient post-processing techniques namely noise removal, shape criteria, elliptic curve fitting and face/nonface classification are proposed in order to further refine skin segmentation results for the purpose of face detection.
展开▼