Face detection based on skin color model and connected component with template matching

Face detection has been the most important phase in identifying facial expressions. To detect a face has been more difficult and since then more methods have been evolving to simplify the task. One such method is to first segment the image based on the skin area and then to detect the face. The approach of this paper is to segment facial region based on L*a*b color model, apply some efficient parameters to detect the skin area of a face, apply morphological operations and draw bounding box using connected component to detect the face and match it with the face template to register the region as face. The experiments observed that the skin color model based approach for face detection has an accuracy of 92% and face registration using template matching has an accuracy of 98%.