Comparative analysis of skin color model for face detection

Skin color detection plays an important phase in identifying the face in images. Detecting face has become difficult because of the complexity in facial features and the similarity between those features. To identify a face, one of the basic step is to segment the image based on skin color. The main objective of the paper is to find a color model which is more suitable and shows a good performance in detecting a face. This paper compares each of the skin color models namely HSV, YCBCR, L*a*b for better accuracy. On such comparison, a hybrid skin color model is derived by combining the suitable color component from the three skin color models. After Morphological operations and using connected components a face is detected. After experiments it is observed that the Hybrid color model based skin detection is more suitable with an accuracy of 93%.