Title :
Multimodal biometric systems
Author :
Taouche, Cherif ; Batouche, Mohamed C. ; Berkane, Mohamed ; Taleb-Ahmed, A.
Author_Institution :
Dept. of Math. & Comput. Sci., Univ. of Oum El Bouaghi, Oum EI Bouaghi, Algeria
Abstract :
Biometric is a unique, measurable physiological or behavioral characteristic of a person. The biometric system is one such that can provide accurate and reliable scheme for person verification and authentication. Unimodal biometric systems have to contend with a variety of problems such as noisy data, intra-class variations, restricted degrees of freedom, non-universality, spoof attacks, and unacceptable error rates. Several of these problems can be addressed by deploying multimodal biometric systems that combine two or more biometric modalities. By combining multiple sources of information, these systems improve matching performance, increase population coverage, deter spoofing, and facilitate indexing. Different scenarios and fusion levels are possible and different integration strategies can be adopted to consolidate information in multimodal systems.
Keywords :
biometrics (access control); error statistics; feature extraction; security; biometric modalities; deter spoofing; error rates; fusion levels; intraclass variations; multimodal biometric systems; noisy data; nonuniversality; person authentication; person verification; restricted degrees of freedom; spoof attacks; unimodal biometric systems; Biomedical imaging; Face; Face recognition; Fingerprint recognition; Image recognition; Irrigation; Support vector machine classification; Biometrics; Fusion level; Multimodal Biometrics; Multimodal biometric Databases; Unimodal Biometrics;
Conference_Titel :
Multimedia Computing and Systems (ICMCS), 2014 International Conference on
Conference_Location :
Marrakech
Print_ISBN :
978-1-4799-3823-0
DOI :
10.1109/ICMCS.2014.6911308