Title :
Thermal face recognition in an operational scenario
Author :
Socolinsky, Diego A. ; Selinger, Andrea
Author_Institution :
Equinox Corp., Baltimore, MD, USA
fDate :
27 June-2 July 2004
Abstract :
We present results on the latest advances in thermal infrared face recognition, and its use in combination with visible imagery. Previous research by the authors has shown high performance under very controlled conditions, or questionable performance under a wider range of conditions. This paper shows results on the use of thermal infrared and visible imagery for face recognition in operational scenarios. In particular, we show performance statistics for outdoor face recognition and recognition across multiple sessions. Our results support the conclusion that face recognition performance with thermal infrared imagery is stable over multiple sessions, and that fusion of modalities increases performance. As measured by the number of images and number of subjects, this is the largest ever reported study on thermal face recognition.
Keywords :
face recognition; feature extraction; infrared imaging; principal component analysis; operational scenarios; outdoor face recognition; thermal infrared face recognition; visible imagery; Face recognition; Image databases; Image recognition; Infrared imaging; Optical imaging; Probes; Testing; Thermal degradation; Thermal expansion; Thermal sensors;
Conference_Titel :
Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on
Print_ISBN :
0-7695-2158-4
DOI :
10.1109/CVPR.2004.1315275