This paper presents an efficient algorithm for iris recognition using support vector machine, and genetic and evolutionary feature extraction techniques. The novelty of this research effort is that we deploy a preprocessing method in an effort to localize the non-ideal iris images accurately. The SVM method incorporates the spatial information into the level set-based curve evolution approach and regularizes the level set propagation locally. The proposed iris localization scheme based on SVM avoids the over-segmentation and performs well against blurred iris/sclera boundary.


Furthermore, we apply a genetic and evolutionary feature extraction (GEFE) technique, which uses genetic and evolutionary computation to evolve modified local binary pattern (MLBP) feature extractor to elicit the distinctive features from the unwrapped iris images. The MLBP algorithm combines the sign and magnitude features for the improvement of iris texture classification performance. The identification and verification performance of the proposed scheme is validated using the CASIA version 3 interval dataset.