An Iris Recognition Algorithm of Multiple Features Extraction and Fusion
Бо Лю, Zhen Zhang, Long Li · 2016
In this paper, an iris recognition algorithm of multiple features extraction and fusion was proposed, which was different from the classical iris recognition algorithm that focused on a single texture feature.Firstly, the collected iris images were preprocessed.Secondly, features of preprocessed images were extracted by using Log-Gabor filter and Haar wavelet, and values of similarity were calculated by adopting Hamming Distance and Weighted Euclidean Distance methods.Finally, the Logistic Regression Classifier was used to fuse and classify the values of similarity.The experimental results verified the effectiveness of the algorithm, and a higher correct recognition rate was gained.