Score level fusion of multimodal biometrics using triangular norms

• Published in: Pattern recognition letters 2011-10, Vol.32 (14), p.1843-1850
• Main Authors: Hanmandlu, Madasu, Grover, Jyotsana, Gureja, Ankit, Gupta, H.M.
• Format: Article
• Language: English
• Subjects: Applied sciences; Artificial intelligence; Biometrics; Computer science; control theory; systems; Connectionism. Neural networks; Cryptography; Decidability index; Exact sciences and technology; Information theory; Information, signal and communications theory; Multimodal authentication; Pattern recognition; Score level fusion; Signal and communications theory; Signal processing; Telecommunications and information theory; Triangular norms
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2011.06.029

► Score level fusion using t-norms. ► Fusion tested on two hand based databases. ► Achieved the genuine acceptance rates as good as 100% against FAR of 0.01%. ► Two performance criterion tested: (i) receiver operating characteristic, (ii) decidability index. A multimodal biometric system that alleviates the limitations of the unimodal biometric systems by fusing the information from the respective biometric sources is developed. A general approach is proposed for the fusion at score level by combining the scores from multiple biometrics using triangular norms (t-norms) due to Hamacher, Yager, Frank, Schweizer and Sklar, and Einstein product. This study aims at tapping the potential of t-norms for multimodal biometrics. The proposed approach renders very good performance as it is quite computationally fast and outperforms the score level fusion using the combination approach (min, mean, and sum) and classification approaches like SVM, logistic linear regression, MLP, etc. The experimental evaluation on three databases confirms the effectiveness of score level fusion using t-norms.