Iris recognition using independent component analysis

Abstract

This paper develops a new method for iris recognition based on independent component analysis. The iris recognition consisted of three major components: image preprocessing, feature extraction and classification. A three-step multiscale approach was employed in image preprocessing to realize iris localization, normalization and enhancement. In iris feature extraction, an efficient approach called independent component analysis was used which was statistically independent to establish features for iris region of interest. Under the same experimental conditions, comparisons with the existing methods demonstrate that the proposed method has an emerging performance.