Multi-fingerprint Information Fusion for Personal Identification Based on Improved Dempster-Shafer Evidence Theory

With the rapid development of the social information, more attention has been paid to the accurate and efficient personal identification methods recently. Since the personal fingerprints are unique and readily available for use, fingerprint identification techniques have been widely used in many applications. However, these methods have some inherent limitations in accuracy due to the varieties of the fingerprint images in quality. Hence, an improved information fusion method based on D-S evidence theory is proposed in this paper to combine fingerprint information together for personal identification. Experimental results show that the performance of the proposed algorithm can well solve the evidence conflict problem and effectively improve the precision and performance of fingerprint identification.