Front human face detection method based on sensitive area

The invention discloses a front human face detection method based on a sensitive area. The method comprises the following steps that a virtual coil is set and the position and the size of the sensitive area are determined; the motion foreground in the sensitive area is detected and tracked through background modeling; the candidate area of the human face is detected through the Adaboost algorithm of Harr-like characteristics; some limitation conditions are set to exclude non-front human face images according to the color characteristics of the human face and simplified shape characteristics. According to the front human face detection method based on the sensitive area, due to the fact that the sensitive area is set and the motion foreground is detected, the efficiency of the follow-up Adaboost detection algorithm is improved, and the detection accuracy is improved through the later skin color and shape verification.