Facial Gesture Identification Using Lip Contours

Abstract

This paper describes a robust technique to determine happy/sad/neutral facial gestures of humans by processing an image containing human face. It aims to do away with the cumbersome process of training the computer with images and thereby significantly reducing the processing time. In this technique human face is identified using skin color identification on various spaces like HSV and YCbCr. Segmented features of face like the lips are determined using unique face feature determination. Contour of lips formed for different human moods are analyzed to identify, facial gesture. Edge detection of lips, followed by morphological operation, gives lip structure. Pattern analysis of lips using the unique histogram algorithm and subsequent comparison with different facial gesture icons gives facial gesture of human being in an image. This technique when tested on a huge database of human images under varying lightning conditions gave acceptable accuracy rates and was found fast enough to be used in real time video-stream