EER ANALYSIS OF MULTIMODAL BIOMETRIC IDENTIFICATION  SYSTEM

Author’s Name : Dr A Jagadeesan | R M Madhumathi

Volume 02 Issue 02  Year 2015  ISSN No:  2349-252X  Page no: 7-12

Abstract -People find difficult to remember long cryptographic keys. Therefore researchers for a long time have been investigating ways to use biometric features of the user rather than memorable password or passphrases, in an attempt to produce tough and repeatable cryptographic keys. The goal is to integrate the volatility of the user’s biometric feature into the generated keys, so as to construct a key unpredictable to a hacker who is deficient of important knowledge about the user’s biometric .In earlier research, they have incorporated multiple biometric modalities into cryptographic key generation to provide better security. In this proposed approach, extraction of Minutiae points from fingerprint using Image Processing and Texture (MIPT) feature from iris are fused for the cryptographic key generation. The multimodal biometric identification system’s effectiveness is measured by its accuracy and security. Performance analysis is carried out by calculating Equal Error Rate (EER) values for different databases between the existing and the proposed approach. Lower values of EER indicate the proposed approach accuracy. For providing better security, the False Not Matching Rate (FNMR) values of the proposed approach are less than the existing approaches.

Keywords –Chinese Academy of Sciences Institute of Automation (CASIA) iris database, Fingerprint Verification Competition (FVC), Equal Error Rate (EER), False Matching Rate (FMR), False Non-matching Rate (FNMR)