Eyelid Detection in Localized Iris Images

Abstract

Localization of human eye (iris) in a non invasive fashion with accuracy has great significance. Iris localization is the back bone of iris recognition systems. In this paper a novel method to localize the eyelid is presented. Iris is localized by applying the texture analysis approach. To find the upper eyelid, a rectangular average filter (size two by five) is applied to the segment above iris center and between left and right boundaries of iris. It is followed by sobel horizontal filter. Points of pupil and iris boundaries are removed and a parabola which best fit among the remaining points. This parabola is the required upper eyelid. Lower eyelid is obtained using the same method. Experimental results show that proposed method is very effective