A Novel Method for Eye Corner Detection Based on Weighted Variance Projection Function

A novel eye corner detection method is presented in this paper. The method is capable of detecting a pair of inner and outer eye corners from a complex background. Faces and eyes are first detected from the image by Adaboost with Haar-like features. Next, the potential area of the eye corner is determined based on variance projection function. In view of the corner characteristics of the eye corner, the weighted variance projection function is proposed to locate the eye corner within the potential area, which combines Harris´s response function with variance projection function. The robustness and accuracy of the proposed method are demonstrated in experiment.