Optimal Features Subset Selection and Classification for Iris Recognition. (7th April 2008)

• Record Type: Journal Article
• Authors: Roy, Kaushik; Bhattacharya, Prabir
• Other Names: Lam Kenneth M. Academic Editor.
• Is Part Of: EURASIP journal on image and video processing. Volume 2008(2008)
• Publication Date: 2008-04-07
• Subjects: Image processing -- Digital techniques -- Periodicals; Digital video -- Periodicals; Traitement d'images; Vidéo numérique; Digital video; Image processing -- Digital techniques; Periodicals; Electronic journal; Electronic journals; 621.367
• DOI: 10.1155/2008/743103
• Languages: English
• ISSNs: 1687-5176

Abstract

Abstract : The selection of the optimal features subset and the classification have become an important issue in the field of iris recognition. We propose a feature selection scheme based on the multiobjectives genetic algorithm (MOGA) to improve the recognition accuracy and asymmetrical support vector machine for the classification of iris patterns. We also suggest a segmentation scheme based on the collarette area localization. The deterministic feature sequence is extracted from the iris images using the 1D log-Gabor wavelet technique, and the extracted feature sequence is used to train the support vector machine (SVM). The MOGA is applied to optimize the features sequence and to increase the overall performance based on the matching accuracy of the SVM. The parameters of SVM are optimized to improve the overall generalization performance, and the traditional SVM is modified to an asymmetrical SVM to treat the false accept and false reject cases differently and to handle the unbalanced data of a specific class with respect to the other classes. Our experimental results indicate that the performance of SVM as a classifier is better than the performance of the classifiers based on the feedforward neural network, the k -nearest neighbor, and the Hamming and the Mahalanobis distances. The proposed technique is computationally effective with recognition rates of 99.81% and 96.43% on CASIA and ICE datasets, respectively.