Abstract
AbstractBiometric is emerging and promising technology to identify and authenticate human being. It is more robust, accurate, and accurate. It is hard to imitate, forge, share, distribute and cannot be stolen, forgotten. After September 11, 2001, incident, the biometric technologies are focused more. Integrating more than one biometric trait yields a promising solution to provide more security. It manages the variety of demerits in unimodal biometric systems such as non-universality, noise in sensed data, intra-class variations, distinctiveness, and spoof attacks. The traditional way of authentication a human and their identity is resolved. The proposed method proves with experimental results on multimodal biometric algorithm for authentication using normalized score-level fusion techniques and hybrid Genetic Algorithm and Particle Swarm Optimization for optimization in order to reduce the parameters considered for evaluation as false acceptance rate and false rejection rate and to enhance accuracy. In this proposed research work, it integrates iris, finger vein, and finger print biometric traits chosen for their best biometric characteristics. The experiment is conducted by SDUMLA-HMT database, and the state-of-art algorithm is evaluated by metrics as false acceptance rate, false rejection rate, equal error rate, and accuracy for proving that the claimed identity as genuine or imposter. KeywordsMultimodal biometricsGenetic AlgorithmParticle Swarm Optimization
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call