Face detection and facial feature extraction based on a fusion of knowledge based method and morphological image processing

Abstract

Detection of human face from an image is a very difficult process. There are many reasons that affect the detection process such as lighting condition, shadows, facial expression etc. Thus facial feature extraction itself becomes a difficult task. In order to propose an efficient method for facial feature extraction, we used the characteristic features of nostrils, eyes lips etc. In our method we assume that frontal face image is readily available. At first face regions detected by detecting the eye regions. After detecting the face region other feature points such as nostril, corners of eyes, corners of lips etc are extracted. At first eye pairs are obtained by finding and verifying possible eye regions. After detecting the eye regions, the distance between the eyes is used to find a possible face candidate. Next, the face is divided into different regions and facial features are extracted from the corresponding regions.