A Novel Eye Location Algorithm based on Radial Symmetry Transform

A novel and robust eye location algorithm is proposed in this paper. The algorithm is based on a low level, context free generalized symmetry transform. Once the regions of interest are detected, characteristics of eyes can be used to improve detection results. The algorithm is tested using 1460 face images of the BioID database and 2730 images of the BANCA database. A fully automatic face verification system has also been developed using this eye location algorithm. The system was one of the top performers in the 2004 International Face Verification Competition