Quality driven iris recognition improvement

The purpose of the work presented in this paper is to adapt the feature extraction and matching steps of iris recognition to the quality of the input images. To this end we define a GMM-based global quality metric associated to a pair of normalized iris images. It quantifies the amount of artifact in these images as well as the amount of texture in artifact-free regions. First we use this metric to adjust, for each pair of irises, the proportion of the normalized image selected on a local quality criteria for feature extraction. This approach is tested with two matching techniques: one performs a bit to bit comparison of binary feature vectors and the other one computes local cross-correlations between real valued vectors. We show that our approach is effective with both techniques. Then we use our metric to choose the matching technique that is best adapted to each image pair in order to make a good compromise between accuracy and speed.