Improving identification accuracy on low resolution and poor quality iris images using an artificial neural network–based matching metric

Abstract

The iris is currently believed to be one of the most accurate biometrics for human identification. The majority of fielded iris identification systems use fractional Hamming distance to compare a new feature template to a stored database. Fractional Hamming distance is extremely fast, but mathematically weights all regions of the iris equally. Research has shown that different regions of the iris contain varying levels of discriminatory information when using circular boundary assumptions. This research evaluates four statistical metrics for accuracy improvements on low resolution and poor quality images. Each metric statistically weights iris regions in an attempt to use the iris information in a more intelligent manner. A similarity metric extracted from the output stage of an artificial neural network demonstrated the most promise. Experiments were performed using occluded, subsampled, and motion blurred images from the CASIA, University of Bath, and ICE 2005 databases. The neural network-based metric improved accuracy at nearly every operating point.