New Method of Iris Recognition Using Dual Tree Complex Wavelet Transform

We used an iris image collection derived from UPOL (University Palacky, OLomouc) database to test iris image identification with a new method. We extracted texture information from a and b components of Lab converted images. We circularly scrolled the iris, extracting, at equal angles, square areas to which we applied dual-tree complex wavelet transform (DTCWT). In order to compute features, we used the average energy of all the DTCWT coefficients for each subimage. We compared the feature vectors using the Euclidean and the Hamming distances. Our results are comparable to those obtained with Daugman's algorithm.