Iris Recognition: Measuring Feature's Quality for the Feature Selection in Unconstrained Image Capture Environments

Iris recognition has been used for several purposes. However, current iris recognition systems are unable to deal with noisy data and substantially increase their error rates, specially the false rejections, in these conditions. Several proposals have been made to access image quality and to identify noisy regions in iris images. In this paper we propose a method that measures the quality of each feature of the biometric signature and takes account into this information to constraint the comparable features and obtain the similarity between iris signatures. Experiments led us to conclude that this method significantly decreases the error rates in the recognition of noisy iris images, resultant from capturing in less constrained environments