A dynamical systems novel approach for accurate human eyes location

AbstractTo accurately locate human eye features, such as eye contours, iris boundaries and the coordinates of pupil centers and canthi, a hierarchical approach was proposed. First, an AdaBoost based eye detector was trained for extracting the sub-images containing eyes areas, and the sub-images were enhanced by single-scale Retinex algorithm. Second, the pupil centers and iris boundaries were located by gradient Hough circle transform in the sub-images. Third, the eyes areas were segmented by FCM clustering for constructing the initial signed distance function which was the Level Set function of C-V Model. Finally, the eye contours and canthi were located using C-V Model. With the combination of FCM clustering and C-V Model, the convergent speed of C-V Model was increased by 64.1% on the Purdue AR face test set, while the locating accuracy was increased by 8.3%. This approach is immune to complicated background and illumination changes, showing its high robustness. Results prove the efficiency of this app...