Dempster-Shafer theory based classifier fusion for improved fingerprint verification performance

• NCJ Number: 305865
• Date Published: 2006
• Author(s): Richa Singh; Mayank Vatsa; Afzel Noore; Sanjay K. Singh
• Length: 9 pages
• Grant Number(s): 2003-RC-CX-K001
• Agencies: NIJ-Sponsored
• Publication Type: Research (Applied/Empirical)

Annotation

This paper presents a classifier fusion algorithm based on Dempster Shafer theory that improves the performance of fingerprint verification.

Abstract

The proposed fusion algorithm combines decision induced match scores of minutiae, ridge, fingercode, and pore-based fingerprint verification algorithms and provides an improvement of at least 8.1% in the verification accuracy compared to the individual algorithms. Further, proposed fusion algorithm outperforms by at least 2.52% when compared with existing fusion algorithms. The authors also found that the use of Dempster’s rule of conditioning reduces the training time by approximately 191 seconds. (Published Abstract Provided)