A heuristically guided hybrid approach to face detection for content based image retrieval in internet images

Content based image retrieval (CBIR) from the Internet often requires human face detection against a cluttered background. In this paper, a solution to this problem using colored images is presented. The method combines human skin color detection with knowledge based heuristics for efficient and robust face detection. Skin colored clusters are extracted from the image using color distribution of human skin. The reduced data set is processed by neural networks to detect various facial feature candidates. Common knowledge based heuristics are applied to the detected facial feature candidates. Face is detected only when both the color and features match the human face. The proposed method, which can detect multiple faces in an image, is invariant to scale and position.