An Improved Iris Recognition Method Based on Wavelet Packet Transform

Abstract

Wavelet packet decomposition transformation is an extension of wavelet transformation, which can achieve more refined decomposition and get more wavelet packet subgraphs. In order to improve the recognition accuracy of iris, an improved iris recognition algorithm based on wavelet packet transform is proposed. First locate and normalize the inner and outer edges of the iris, then obtain the wavelet packet subgraphs through wavelet packet decomposition, calculate the coefficients of each subgraphs to obtain the iris feature vectors, and then calculate the Hamming distances of the corresponding feature vectors of the two iris images, according to different subgraphs. The calculated coefficients are identified by the weighted Hamming distance classifier.