We present an approach t detect eyes in color images. First of all, RGB facial image is converted to YCbCr one. According to YCbCr facial image, the proposed algorithm constructs two EyaMaps, one map from luminance component (EyeMapL) and yhe other from chrominance component (EyeMapC). When the two separate EyeMaps are constructed, we combine them to make final EyeMap. We use final EyeMap to generate potential eye candidates and them perform an extra phase on these candidates to determine suitable eye pair. This extra phase consists of flexible thresholding and geometrical tests. We test our approach on CVL and Iranian database. Simulation results showed this phase improved the correction detection rate by about 12.5% and reach 98.5% success rate on the average.

Keywords