Multimodal Biometric In Human Identification Of Finger Vein Patterns Using Score Level And GSA

Biometric and multi biometric science play an important role in human authentication systems. Among many types of biometric model finger vein pattern is one of the most reliable and secure biometrics due to its invariability and safety from stealth. Since there are so much of algorithms carried out in our existing system, SVM (support vector machine) used for human authentication which has the ability to achieve maximal computational efficiency, fast spatiotemporal and has the ability to classify human motion patterns. However there are so many algorithms carried out for identification fingerprint faces some disadvantages such as sensibility to noise and spoof attack, here SVM requires large amount of training data to identify. To overcome this, thus proposing a system using heuristic method and gravitational search algorithm had advantages of solving non differentiable and multimodal problems effectively, requires less computation. The Gravitational Search Algorithm is based on Newton’s law of GRAVITY and MOTION .The performance is evaluated using FAR, FRR, EER.