Iris feature extraction algorithm based on wavelet transform and directional vector
Gui Feng · Jisuanji gongcheng yu sheji · 2008
Irises can be distinguished mainly due to textural difference among them.In order to acquire a high recognition rate,the textural information of iris images must be extracted effectively.A new iris feature extraction method is presented by taking advantages of 2-D wavelet transform.The basic principle of the method is as follows.In view of iris textural intensity variation,for the low-frequency components of multi-resolution decomposition,directional vector along four directions is obtained,and iris code is formed in the end.According to test,the algorithm can enhance iris recognition rate.Furthermore,algorithm is simple and fast.