A New Iris Recognition Method based on Neural Networks

Abstract: This paper presents a novel approach of iris recognition based on feedforward neural networks. The features used in this approach are based on the contour of the iris-pupil boundary obtained from radius vector functions and is named iris signature. The proposed technique used is translation, rotation, and scale invariant. The classication is performed using two different neural network structures, the Multilayer Feedforward Neural Network (MFNN) and the Radial Basis Function Neural Network (RBFNN). These feedforward neural networks have not been applied before on iris signatures. Since iris signature is 1D, it simplies the structure of neural networks. Hence the proposed method has lesser complexity than the existing neural networks based techniques. The results obtained from a small size data base are very promising