No abstract

Biometric based authentication is playing a very important role in various security related applications. A novel multimodal biometric verification based on fingerprint, palmprint and iris with matching score level fusion using Mathematical Normalization is proposed in this paper. In feature extraction stage of unimodal, features of each modality are extracted by applying wavelet decomposition using 6 different wavelet families and 35 respective wavelet family members. Further, the three optimal combinations of unimodal systems based on equal error rate achieved by wavelet(s) are chosen for development of multimodal biometric system. In matching score level fusion, along with wellknown normalization techniques-Min-max, Tan-h and Zscore, the performance of multimodal systems are also analyzed using Mathematical Normalization (Math-norm) followed by product, weighted product, sum and average fusion rule. The experiments are conducted on database of 100 different subjects from publically available FVC2006, CASIA V1 and IITD database of fingerprint, palmprint and iris, respectively. The experimental results clearly show that Mathematical Normalization followed by weighted product has given promising accuracy with equal error rate (EER) of 0.325%.

<p>Biometric based personal authentication is playing a vital role in various security based applications. This paper presents the effective fusion of fingerprint, palmprint and iris traits at decision level. Combining different traits at the decision level is a challenging task due to less information available at this level. The focus of the work is to examine the performance of multimodal biometrics at decision level fusion in three different i.e. serial, parallel and hierarchical modes of operation. Serial mode is performed by taking unimodals serially while parallel mode of operation is carried out by processing all modals simulatenously using Majority Voting Rule and the hierarchical mode of operation is performed with proper combination of traits in parallel and serial mode using AND and OR rule. The experiments are performed on 100 different users from publically available FVC2006 fingerprint database, CASIA V1 palmprint database and IITD iris database. The experimental results suggest that proper fusion of different traits in hierarchical way can give best performance even at decision level fusion as compared to serial and parallel mode of operation.</p>

Multimodal biometrics is the frontier to unimodal biometrics as it integrates the information obtained from multiple biometric sources at various fusion levels i.e. sensor level, feature extraction level, match score level, or decision level. In this article, fingerprint, palmprint, and iris are used for verification of an individual. The wavelet transformation is used to extract features from fingerprint, palmprint, and iris. Further the PCA is used for dimensionality reduction. The fusion of traits is employed at three levels: feature level; feature level combined with match score level; and feature level combined with decision level. The main objective of this research is to observe effect of combined fusion levels on verification of an individual. The performance of three cases of fusion is measured in terms of EER and represented with ROC. The experiments performed on 100 different subjects from publicly available databases demonstrate that combining feature level with match score level and feature level with decision level fusion both outperforms fusion at only a feature level.

No abstract