Quality-dependent fusion system using no-reference image quality metrics for multimodal biometrics

Abstract

Biometric acquired and processed data quality is the prime 
influences, which will affect the performance of the whole 
biometric system. Hence, aforementioned is essential to 
control the quality of acquired data to devise a suitable 
biometric system. This paper presents a robust multimodal 
biometric system using quality dependent expert fusion 
system. We Presents work, on a novel quality assessment 
metrics for Fingerprint, Palmprint, and Iris. The originality 
of this work contributing with blind image quality measures.  
The projected quality metrics associates with two type of 
quality measure a) Image-based quality as well as b) 
pattern-based. We have explore and comprehend the 
associated various quality assessment in the biometrics. 
Benefits of the proposed quality matric have been illustrates 
on six benchmark database. The performance of the 
proposed quality measures demonstrates on multimodal 
biometric system is evaluated on a public dataset and 
demonstrating its recognition accuracy with respect to EER. 
Result shows the efficiency of detecting the kind of 
alterations. Kolmogorov-Smirnov (KS) test statistics shows 
0.84 to 0.94 outperformed as compared to NFIQ.