FUSION OF MULTIMODAL BIOMETRICS OF FINGERPRINT, IRIS AND HAND WRITTEN SIGNATURES TRAITS USING DEEP LEARNING TECHNIQUE

Abstract

Due to expanding interest for the data security and safety guidelines everywhere, biometric
authentication technology has been generally utilized in our regular day to day existence. With respects to this,
multi-modal biometric innovation has acquired attention and became famous because of the capacity to a
overcome the drawbacks of uni-model biometric frameworks. In Present research, novel multi biometrics
recognition proof solution is developed, that depends to deep learning techniques for perceiving human utilizing
multi biometric traits of Iris pattern, finger print data and offline signature biometrics. Framework of design
depends on Deep Neural Networks (DNNs), for separating the parameters & classification of the image utilizing
soft max based technique. To foster the framework, deep learning models are joined iris, finger print and off-line
signature. To construct the VGG-19 network was utilized, and Adam streamlining technique has been applied for
unmitigated to measure the degree of inequality was utilized as a misfortune work. A few strategies to stay away
from overfitting were applied, like picture increase and drop-out procedures. For combining the deep learning
networks, different combinations are utilized to investigate the impact of techniques on acknowledgment
execution, accordingly component and score-level combination approach was applied. The exhibition of proposed
framework is experimentally by directing a few trials to the SDUMLA-HMT data set, which is multi-modal
biometric data set. Acquired outcomes showed that involving triple biometrics attributes in biometric distinguished
proof frameworks got preferred outcomes over utilizing a couple biometric characteristics. The outcomes
additionally shows that our methodology serenely beat other condition of- - the-craftsmanship techniques by
accomplishing a precision of 99.11% on an element degree combination procedures and of 99.21 percent
accuracy of various strategy for fusion at score level.