A new facial key features location algorithm in color images

Facial feature accurately location is the critical step in face recognition. A new facial key features location algorithm in color images by the color information of facial features is presented. Since the RGB three components of eyes region are very close, the sum of RGB three components difference is calculated as eye feature. Then the eye center points are located by priori information. Combining redness with the sum of RGB three components difference, the whole mouth is effectively extracted to locate the mouth center. Experimental result on four databases with 5649 images indicates the proposed method is insensitive to the variant expression and pose, and the feature location accuracy rate is 95.52%.