Information fusion in low-resolution iris videos using Principal Components Transform

The focus of this work is on improving the recognition performance of low-resolution iris video frames acquired under varying illumination. To facilitate this, an image-level fusion scheme with modest computational requirements is proposed. The proposed algorithm uses the evidence of multiple image frames of the same iris to extract discriminatory information via the Principal Components Transform (PCT). Experimental results on a subset of the MBGC NIR iris database demonstrate the utility of this scheme to achieve improved recognition accuracy when low-resolution probe images are compared against high-resolution gallery images.