Multibiometric Based On Fingerprint Recognition And Face Recognition

Biometric verification systems that use a single biometric indicator often have to contend with noisy sensor data, restricted degrees of freedom and unacceptable error rates. Attempting to improve the performance of individual matchers in such situations may not prove to be effective because of these inherent problems. Multimodal biometric systems seek to alleviate some of these drawbacks by providing multiple evidences of the same identity. These systems also help achieve an increase in performance that may not be possible by using a single biometric indicator.Face and fingerprint verification have been employed in various biometric applications. The fusion of these two biometrics has an advantage in improving verification performance. This paper addresses the problems of building a multimodal biometric verification system on PC, which integrate fingerprint and face to improve performance of verification. In this paper we present a fusion method based on uncertain region. Dividing minutia features of fingerprint into certain and uncertain region could make the performance of verification in certain region better than the original performance. Through integrating uncertain fingerprint data of fingerprint and data of face, the performance of verification in uncertain region can be also improved. By this fusion strategy the whole performance is improved.