Facial area forecast and occluded face detection based on the YCbCr elliptical model

Aiming at the occluded face in the specific environment, the facial area was forecasted by the YCbCr elliptical model , the occluded face was detected in banks or in front of ATMs. The video monitoring sequences were obtained through cameras, an occluded face detection method based on the YCbCr elliptical model was proposed in this paper. Then CamShift target tracking algorithm was applied to face tracking, the connected area of target faces were selected in external ellipses. Finally, the area of the connected region was complicated with the face region which was predicted by the ellipse model. Through a predefined abnormal behavior, whether the occluded face was the abnormal behavior or not could be identified. Experiment results show that the algorithm obtains almost ideal result in the field of detection accuracy rate, false alarm rate and detection and tracking speed.