Learning Liveness Detection and Classification of Iris Images: A Detailed Survey

Iris recognition is most often used for security related applications and mainly suffer from illegal attacks. So an iris recognition system that identifies the fake iris image are much needed. In this paper, we present a novel iris texture representation method called Hierarchical Visual Codebook (HVC) is proposed to encode the texture primitives of iris images and are used for identifying the fake and original iris images. Here we use the Bag-of-words models for statistical feature representation of iris for classification. For accurate and sparse representation of iris texture HVC make use of both locality-constrained linear coding and vocabulary tree. This helps in better visual representation of iris texture, Vector Quantization and the removal of coding errors.