Thermal face recognition in an operational scenario

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.

[1]  J. Beveridge,et al.  Parametric and Nonparametric Methods for the Statistical Evaluation of Human ID Algorithms , 2001 .

[2]  Xin Chen,et al.  PCA-Based Face Recognition in Infrared Imagery: Baseline and Comparative Studies , 2003, AMFG.

[3]  P. Jonathon Phillips,et al.  Meta-analysis of face recognition algorithms , 2001, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[4]  Rama Chellappa,et al.  Robust Face Recognition Using Symmetric Shape-from-Shading , 1999 .

[5]  Andrea Salgian,et al.  Face recognition with visible and thermal infrared imagery , 2003, Comput. Vis. Image Underst..

[6]  Andrea Salgian,et al.  A comparative analysis of face recognition performance with visible and thermal infrared imagery , 2002, Object recognition supported by user interaction for service robots.

[7]  Joseph Wilder,et al.  Comparison of visible and infra-red imagery for face recognition , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[8]  Hyeonjoon Moon,et al.  The FERET evaluation methodology for face-recognition algorithms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Lawrence B. Wolff,et al.  Illumination invariant face recognition using thermal infrared imagery , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[10]  Terrance E. Boult,et al.  Efficient evaluation of classification and recognition systems , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[11]  F. Prokoski.  History, current status, and future of infrared identification , 2000, Proceedings IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications (Cat. No.PR00640).

[12]  Shimon Ullman,et al.  Face Recognition: The Problem of Compensating for Changes in Illumination Direction , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  M. Abidi,et al.  Performance Comparison of Visual and Thermal Signatures for Face Recognition , 2003 .

[14]  Patrick J. Flynn,et al.  Visible-light and Infrared Face Recognition , 2003 .