An Algorithm for Improved Accuracy in Unimodal Biometric Systems through Fusion of Multiple Feature Sets

The major concern in a Biometric Identification System is its accuracy. In spite of the improvements in image acquisition and image processing techniques, the amount of research still being carried out in person verification and identification show that a recognition system which gives 0% FAR (False Acceptance Rate) and FRR (False Rejection Rate) is still not a reality. Multibiometric systems which combine two different biometric modalities or two different representations of the same biometric, to verify a person’s identity are a means of improving the accuracy of a biometric system. The former case however requires the user to produce his biometric identity two times to two different sensors. The image processing and pattern matching activities also increase nearly twofold compared to unimodal systems. In this paper we propose a fusion of two different feature sets, one extracted from the morphological features and the other from statistical features, of the same biometric template, namely the hand vein biometric. The proposed system gives the accuracy of a multimodal system at the speed and cost of a unimodal system.