Improvement of face detection using spatial context information

Abstract

Face detection technology is an essential step of any face processing system such as facial recognition system, video surveillance, and human computer interaction (HCI). Detection performance and speed are important factors of face detection task which is used in the real time face processing system such as video surveillance. The region containing faces can be understood as a part of the image. People prefer to allocate concerned objects on the center of the image rather than the boundary when they take a picture. The tendency of people arranging concerned objects on the center of the scene aims to distinguish the object from other objects and to accentuate objects in an image. Hence, this paper proposes a face detection method using the spatial context information. Experiments were performed to verify the proposed method and experimental results showed that the proposed face detection method can efficiently reduce the false positive rate as well as the runtime of face detection.