Using residual images with BSIF for iris liveness detection

Abstract

Deploying iris recognition systems in several security areas emphasized the importance of developing iris liveness methods. These methods verify if the iris sample acquired for authentication is fake or real. Recently, Binarized Statistical Image Features (BSIF) descriptor was successfully applied for that purpose. As BSIF is a powerful descriptor based on Local Binary Pattern (LBP) descriptor, we have supposed that enhancements that have worked before with LBP could work with BSIF as well. Widening a previous work, four public datasets representing printed, plastic, synthetic, and contact lens attacks were evaluated using 8-bit BSIF in both modes segmented and unsegmented eye images. Contact lens attack was the most challenging attack, especially in the unsegmented scenario. In this paper, a new method is proposed using residual images with BSIF to enhance the results of contact lens databases. Three high pass filters were applied separately before the feature extraction phase to improve the discrimination ability of BSIF. Clarkson contact lens database was used for evaluation in both modes segmented and unsegmented eye images. The results were promising in the unsegmented scenario and the three filters enhanced in the results with 8.6667%, 10%, and 18.3333%. The application of these filters with BSIF could be useful for other computer vision tasks like face liveness detection.