Evaluation of multiple enrollment for fingerprint recognition

Abstract

Fusion of multiple impressions resulting from multiple fingerprint enrollments is one of the ways often used to improve fingerprint recognition performance. In this research, we perform an evaluation of the effectiveness of using multiple enrollment in fingerprint recognition systems. We design a multiple enrollment algorithm and use it together with existing fingerprint recognition techniques to carry out the evaluation. Our experimentation results and evaluations show that multiple enrollment as whole outperforms single enrollment. Multiple enrollment in experiment (1) improved the recognition performance by 83% from EER 1 of 0.75% to EER of 0.13% with FVC2000-DB2, and by 79% from EER of 1.14% to EER of 0.28% with the SAS-DB2 fingerprint database. On the other hand, the multiple enrollment in experiment (2) improved the recognition performance by 71% from EER of 6.14% to EER of 1.75% with FVC2000-DB2 and improved recognition performance by 53% from EER of 14.97% to EER of 6.94% with SAS-DB2 fingerprint database.