A Novel Method of Iris Feature Extraction Based on the ICM

The feature of iris image would be exactly and efficiently extracted difficultly by common methods. Considering that the intersecting cortical model (ICM) can be used to directly extract pertinent information from a variety of images for the purpose of recognition, we firstly propose a novel method of feature extraction for iris image based on the ICM. The results show that our method is feasible, potential and effective in obtaining feature from iris image. In our method, a series of binary images are firstly produced from the input iris image through the ICM. Entropy sequence can be gained from these binary images. And then phase information is obtained from entropy sequence. This phase information is taken as feature vector with the uniqueness for different individuals. Finally, we carry out matching experiment using the phase information. The advantages, disadvantages and further work are pointed out in the end.