Identification of Human Skin Regions Using Color and Texture

A novel approach identifying and segmenting skin regions within images is presented in this paper. The identification and recognition of facial regions are a central focus of this work. A set of standard images containing facial/skin objects is first manually segmented into the interested regions. These regions are utilized in the training the system. Dominant color features (i.e., the most frequently occurring quantized colors) along with texture features generated from the co-occurrence matrix are extracted from the training regions. An example image is then presented to the system. The image undergoes a standard image segmentation algorithm that splits the image into consistent objects. The same color/texture features are extracted from the example regions. A similarity measurement is computed and the regions of the example image are subsequently classified as skin/non skin regions. Results are shown for several standard mpeg such as Foreman, Salesman, Miss America, and others.