The Community for Technology Leaders
2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance (2006)
Sydney, NSW, Australia
Nov. 22, 2006 to Nov. 24, 2006
ISBN: 0-7695-2688-8
pp: 50
Riad Hammoud , Delphi Electronics and Safety, USA
Ognjen Arandjelovic , University of Cambridge, UK
Roberto Cipolla , Delphi Electronics and Safety, USA
ABSTRACT
Recognition algorithms that use data obtained by imaging faces in the thermal spectrum are promising in achieving invariance to extreme illumination changes that are often present in practice. In this paper we analyze the performance of a recently proposed face recognition algorithm that combines visual and thermal modalities by decision level fusion. We examine (i) the effects of the proposed data preprocessing in each domain, (ii) the contribution to improved recognition of different types of features, (iii) the importance of prescription glasses detection, in the context of both 1-to-N and 1-to-1 matching (recognition vs. verification performance). Finally, we discuss the significance of our results and, in particular, identify a number of limitations of the current state-of-the-art and propose promising directions for future research.
INDEX TERMS
null
CITATION
Riad Hammoud, Ognjen Arandjelovic, Roberto Cipolla, "On Person Authentication by Fusing Visual and Thermal Face Biometrics", 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, vol. 00, no. , pp. 50, 2006, doi:10.1109/AVSS.2006.86
86 ms
(Ver )