Robust human face detection for moving pictures based on cascade-typed hybrid classifier

Face detection has been a key step in face analysis systems for decades. However, it is still a challenging task due to the variation in image background, view, pose, facial expression, etc. This paper proposes a simple and effective tool to detect human faces in moving pictures under such conditions. An improved approach aiming to reduce impacts of illumination, scale and connection of faces to receive rapidly skin homogeneous regions considered as the most potential face candidates is presented. A cascade-typed hybrid classifier, applied in retrieved face candidates, is based on template matching and appearance-based method providing a robust detection of multiply posed and viewed faces. This verification achieves advantages of the powerful discrimination of Local Binary Patterns (LBPs) and the high speed detection capability of embedded Hidden Markov Models (eHMMs). Experiments were performed out with different image databases and video sequences so that the system shows effective to detect human face for real-time uses.