Robust Iris Feature Extraction using Dual Tree Complex Wavelet Transform

This paper represents a new method for iris recognition using the dual tree complex wavelet transform. For the dual filter tree, we select two linear phase biorthogonal filter sets with odd and even lengths which is used to filter each signal for quantization to 136 byte iris feature codes. Then the Hamming distance is adopted to match two iris codes. In particular, the appropriate scale for each signal is searched for by minimizing the Hamming distance. The experimental results on CASIA database shows reliability and performance that the performance of this method is better than some algorithms, so it is promising to be used in a personal identification system.