An Efficient Multi-Modal Biometric Sensing and Authentication Framework for Distributed Applications

Abstract

Multimodal biometrics is an emerging technology for distributed data security. Single and multi-user data authentication plays a vital role in commercial or e-governance applications. Many approaches have been implemented in literature to secure the single user data using biometric security systems. Most of these systems are based on static initialization parameters and fixed multi-modal biometric features for data authentication. Also, traditional multi-modal biometric based data authentication schemes are independent of dynamic variation in integrity verification. In order to overcome these problems, a new multi-user based multi-modal authentication framework is designed and implemented on large image data types. In this framework, different biometric features such as IRIS, facial and fingerprint features are used to find the unique integrity of user for data authentication and security process. A new integrity computational algorithm and encryption technique are implemented to provide the strong data integrity verification and data security in distributed applications. Experimental results show that the proposed multi-modal integrity-based encryption model has nearly 7% of computational integrity bit change and 5% of runtime on large dataset.