TY - JFULL AU - Sanghoon Kim and Sun-Tae Chung and Souhwan Jung and Dusik Oh and Jaemin Kim and Seongwon Cho PY - 2007/10/ TI - Multi-Scale Gabor Feature Based Eye Localization T2 - International Journal of Computer and Information Engineering SP - 2688 EP - 2693 VL - 1 SN - 1307-6892 UR - https://publications.waset.org/pdf/3247 PU - World Academy of Science, Engineering and Technology NX - Open Science Index 9, 2007 N2 - Eye localization is necessary for face recognition and related application areas. Most of eye localization algorithms reported so far still need to be improved about precision and computational time for successful applications. In this paper, we propose an eye location method based on multi-scale Gabor feature vectors, which is more robust with respect to initial points. The eye localization based on Gabor feature vectors first needs to constructs an Eye Model Bunch for each eye (left or right eye) which consists of n Gabor jets and average eye coordinates of each eyes obtained from n model face images, and then tries to localize eyes in an incoming face image by utilizing the fact that the true eye coordinates is most likely to be very close to the position where the Gabor jet will have the best Gabor jet similarity matching with a Gabor jet in the Eye Model Bunch. Similar ideas have been already proposed in such as EBGM (Elastic Bunch Graph Matching). However, the method used in EBGM is known to be not robust with respect to initial values and may need extensive search range for achieving the required performance, but extensive search ranges will cause much more computational burden. In this paper, we propose a multi-scale approach with a little increased computational burden where one first tries to localize eyes based on Gabor feature vectors in a coarse face image obtained from down sampling of the original face image, and then localize eyes based on Gabor feature vectors in the original resolution face image by using the eye coordinates localized in the coarse scaled image as initial points. Several experiments and comparisons with other eye localization methods reported in the other papers show the efficiency of our proposed method. ER -