Face Location in Dim-Lightening Coal Mine Surveillance Images

The hue component of face area in coal mine surveillance images is not true of normal school because of nonlinear characteristic of image sample device in dim-lightening surroundings, and its contrast is clearer than that of non-face area. The skin-color of miner´s faces surveillance images of multi angles can be segmented fleetly with the segmentation parameter of hue component which is initialized according to experiments. An average half face template based on the distribution feature of gray level of faces is constructed, which can reduce the contingency of local gray level greatly. The contingency of local information in average face templates will reduce greatly. The speed of template matching and precision of side-face matching is promoted. The results show that the locations of the miners´ faces can be pinpointed fleetly with the method of hue component segmentation and average half face template matching.