A discussion on fusion/confusion at score level in unimodal biometric systems

Fusing biometric information at different levels is one of the widely-preferred techniques for better accuracy. Researchers attempt to decrease error rates by fusing either multiple biometrics or apply sensor-, feature-, score- or decision-level fusion in unimodal biometric systems. Although it incr...

Full description

Saved in:
Bibliographic Details
Published in:2017 25th Signal Processing and Communications Applications Conference (SIU) pp. 1 - 4
Main Authors: Kilic, Muhammed Maruf, Kanak, Alper
Format: Conference Proceeding
Language:English
Published: IEEE 01-05-2017
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fusing biometric information at different levels is one of the widely-preferred techniques for better accuracy. Researchers attempt to decrease error rates by fusing either multiple biometrics or apply sensor-, feature-, score- or decision-level fusion in unimodal biometric systems. Although it increases the complexity of systems, fusion works usually well. However, in some cases score-level fusion may degrade the performance instead of improving the system. In this study a discussion on fusion whether it causes confusion or not is raised by presenting a unimodal face fusion approach. Results show that if fusion is not designed properly, it may cause confusion.
DOI:10.1109/SIU.2017.7960425