Review on Fusion Algorithms for Multimodal Authentication System

  Miss Aarohi Vora,  Dr. Chirag Paunwala,  Dr. Mita Paunwala

Technological revolution in this world is spreading so far that it has replaced knowledge based and token based recognition systems with biometric systems. These systems accurately recognise/authenticate an individual to access his confidential data/accounts. When multiple traits are fused together, it results into highly accurate multimodal systems. This system improvise rate of recognizing an individual. Multiple biometric traits cannot be cloned simultaneously and hence it is highly secured system. The match scores of different persons are sufficient enough to recognise them and differentiate them from each other. The match scores do not require higher storage capacity as well as higher computational complexity. Hence, match score fusion is highly preferable to recognize an individual. This paper therefore reviews algorithms for fusion at match score level with various state of arts namely linear weighted sum rule (LWSR), product rule, majority voting rule, Support vector machine (SVM), Bayesian fusion, fuzzy rule method, etc. The improved performance of fused system is observed from its Receiver Operating Characteristic (ROC) curve. It has been observed that for these methods, TER of a fused system decreases and the GAR of fused system increases i.e. recognition performance of fused system is better as compared to unimodal systems. LWSR is a linear hard decision rule based method. In almost all practical applications nonlinearity exists in scores of different models. So classification based systems are used for fusion. The recognition performance of RBF based QP SVM system is higher as compared to other kernel based systems i.e. GAR of RBF fused system increases and is better as compared to other kernel based QP SVM systems. Classification based methods like SVMs result into higher amount of recognition rate of almost as compared to rule based methods like LWSR.

Keywords- multibiometric systems; rule based methods; classification based methods;LWSR; SVM

Unique Identification Number - IJEDR1502160
Page Number(s) - 911-917
Pubished in - Volume 3 | Issue 2 | May 2015
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Miss Aarohi Vora,  Dr. Chirag Paunwala,  Dr. Mita Paunwala,   " Review on Fusion Algorithms for Multimodal Authentication System", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.3, Issue 2, pp.911-917, May 2015, Available at :http://www.ijedr.org/papers/IJEDR1502160.pdf