Authors: Izem Hamouchene; Saliha Aouat
Addresses: LRIA Laboratory, Computer Science Department, USTHB University, Algiers, Algeria ' LRIA Laboratory, Computer Science Department, USTHB University, Algiers, Algeria
Abstract: Recent science studies are interested in automatic systems without human intervention. The security field is in a great need of automatic identification system based on biometric properties. The uniqueness of the texture present in the human iris is a natural password. In this paper, we propose a novel iris recognition approach based on a combination of two systems. The first system extracts the local variation of the mean and the variance. The second system is based on the rotation invariant neighbourhoodbased binary pattern method (Hamouchene and Aouat, 2014a). Two sets of support vector machines (SVM) are used to train each system. Dempster-Shafer theory is used to distribute unitary mass over the two output sets of SVMs. Finally, the combined belief measures are transformed to a probability by applying the Dezert-Smarandache theory. In the experiments, the proposed system is compared to famous iris recognition systems and obtained better recognition rates.
Keywords: iris recognition system; IRS; neighbourhood-based binary; texture analysis; mean and variance variations; Dempster-Shafer theory; DST; support vector machines.
International Journal of Advanced Intelligence Paradigms, 2019 Vol.14 No.1/2, pp.80 - 106
Received: 14 May 2016
Accepted: 26 Oct 2016
Published online: 14 Oct 2019 *