Open AccessAn Improved Iris Recognition Method Based on Wavelet Packet Transform
Author(s) -
Yonghui Wang,
Haoran Zheng
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1744/4/042239
Subject(s) - wavelet packet decomposition , wavelet , pattern recognition (psychology) , iris recognition , stationary wavelet transform , artificial intelligence , computer science , hamming distance , wavelet transform , cascade algorithm , transformation (genetics) , second generation wavelet transform , feature vector , network packet , mathematics , algorithm , biometrics , computer network , biochemistry , chemistry , gene
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.