A novel multialgoritmic approach for improving accuracy of iris recognition using Haar, multiresolution and new block sum method

Abstract

The basic aim of biometric identification system is to discriminate automatically between subjects in a reliable and dependable way, according to specific-target application. The randomness of iris pattern makes it one of the most reliable biometric traits. The personal identification approaches using mutialgorithmic are more promising now a day. In this paper a multialgoritmic approach for feature extraction using, a new block-sum method, which results in a compact and efficient feature vector, Haar transform and multiresolution feature extraction techniques is used. The experimental results show that this technique gives most promising results as compared to the existing approaches.