Multi-resolution wavelet-based image fusion for iris recognition

Abstract

Iris recognition is one of the most powerful techniques for biometric identification. The requirement of current scenario is to have a simple and efficient scheme for iris recognition with high performance of the system. Existing methods suffer from some undesirable side effects and reduced feature contrast which degrades the quality of the output image. Furthermore, some of these methods are rather complex and this contradicts the concept of the simplicity. Image fusion is an important tool for improving performance in image-based applications such as remote sensing, machine vision, medical imaging and so on. In this paper, an efficient approach for fusion of multiple iris images based on multi-resolution wavelet is presented. Root mean-square error (RMSE) and correlation coefficient (CORR) are used as the assessment metrics for evaluation. The algorithm reduces the elapsed time and accelerates the verification process with high recognition accuracy. The Chinese Academy of Sciences - Institute of Automation (CASIA) iris database is used to simulate the studies. The approach used in the proposed work outperforms existing approaches with the fact that in the proposed iris recognition system, the feature level method preserves the information from the edges.