This paper proposes a novel fingerprint classifier fusion algorithm that accurately matches fingerprint evidence and efficiently adapts to dynamically evolving database size without compromising accuracy or speed.
This paper presents a novel fingerprint classifier fusion algorithm using Dempster-Shafer theory concomitant with update rule. The proposed algorithm accurately matches fingerprint evidence and also efficiently adapts to dynamically evolving database size without compromising accuracy or speed. The authors experimentally validate their approach using three fingerprint recognition algorithms based on minutiae, ridges, and image pattern features. The performance of our proposed algorithm is compared with these individual fingerprint algorithms and commonly used fusion algorithms. In all cases, the proposed Dempster Shafer theory with update rule outperforms existing algorithms even with partial fingerprint image. We also show that as the database size increases, the proposed algorithm is designed to operate on only the augmented data instead of the entire database, thereby reducing the training time without compromising the verification accuracy. (Published Abstract Provided)
Similar Publications
- Understanding the Broader Impacts of Body Worn Cameras on Police Work and Community Perceptions: A Multi-Method Assessment
- Detection of Ignitable Liquid Residues in Fire Debris by Using Direct Analysis in RealTime Mass Spectrometry (DART-MS)
- Flashforward: The Current and Future Applications of Vibrational Spectroscopy for Forensic Purposes