Enhancing iris recognition system performance using templates fusion

Iris recognition has very high recognition accuracy in comparison with many other biometric features. This paper proposes an iris recognition algorithm in which a set of iris images of a given eye are fused to generate a final template using the most consistent feature data. Features consistency weight matrix is determined according to the noise level presented in the considered images. A new metric measure formula using Hamming distance is proposed. Such an algorithm has the capability of reducing the amount of data storage and accelerate the matching process. Simulation studies are made to test the validity of the proposed algorithm. The results obtained ensure the superior performance of such algorithm over any other one.