Efficient iris retrieval using neural networks

Biometrics in high technology refers to the automatic recognition of individuals physiological and behavioral traits which determines their identity. Iris recognition is one of the most reliable and widely used biometric techniques for personal identification and security. The major objective of the work presented here is to accurately recognize the users with iris patterns and with faster computation results. In this paper, we have proposed an architecture that makes use of sobel edge detection, discrete wavelet transform (DWT), four neighbours concept (FNC) for processing the images that achieve higher efficiency. The proposed approach utilizes neural networks for accurate and computationally efficient recognition.