Trinity Journal of Management, IT & Media (TJMITM) Year: 2012 (Jan-Dec), Volume: (3), Issue. (1) First page: (19) Last page: (22) Online ISSN: A/F Print ISSN: 2320-6470 doi:
Multimodal Biometric Authentication System
Rajesh Kumar Jain
1HoD, Comp. Sc. Deptt., Sirifort College of Computer Technology & Mgt, Rohini
Corresponding author email id:
How to cite the Article
A wide variety of applications require reliable and secure verification schemes to confirm the identity of an individual requesting authorized accessing to a specified service. Examples of such applications include secure access to buildings, personal computer systems, laptops, cellular phones and ATMs. In the absence of robust verification schemes, these systems are subject to the tricks of an impostor. Biometric authentication (BA) is a problem of verifying an identity claim using a person’s behavioral and physiological characteristics. Biometric identity authentication is based on a binary classification problem: reject or accept identity claim. The basis of some matching criteria. Several verification systems have been developed based on different biometrics characteristics (fingerprint, face, speech, iris etc) which help to distinguish individuals from each other. Each biometric has its own advantages and drawbacks due to its discriminative power, complexity, robustness involved. Research in last few years has shown that no single biometric system can achieve 100% authentication accuracy. This problem can be alleviated by combining two or more biometric modalities , also known as the field of multimodal biometric authentication. Auser authentication scenario involving two modalities (Face and Speech)  is figured out in Fig. 1. performance and robustness of identity authentication systems can be improved by combining two or more different modalities (speech, face, fingerprint, etc.).
Binary classifiers, biometrics, classifier fusion, feature extraction, support vector machine, ROC.