Infrared Face Temperature Normalization in Fourier Domain
This paper proposes a novel temperature normalization method in Fourier domain, which can lessen the effect on infrared face recognition from ambient temperature based on the idea of statistical learning in the transform domain. Firstly, the infrared face images in different ambient temperatures are transformed to Fourier domain. Secondly, based on statistical theory, the variances of phase spectrum and amplitude spectrum of the infrared face are used to describe the extent affected by the ambient temperature. Then, to achieve the robust information, those parts with big variances in the phase spectrum and amplitude spectrum are discarded and replaced by corresponding mean parts in training database. The main idea of this process is that one can set a suitable threshold for the variance of phase spectrum and amplitude spectrum and find those characteristic points that should be replaced. Finally, to verify the effectiveness of our temperature normalization method, the normalized infrared face can be applied to traditional face recognition system based on classic PCA method. Experimental results show our normalization method can get stable information in infrared face and improve the performance of the infrared face recognition system.
Keywordsdiscrete fourier transform infrared face recognition temperature normalization variance
Unable to display preview. Download preview PDF.
- 2.Wang, Y.: The Principle, Method and Technology of Face Recognition. The Science Press (2010)Google Scholar
- 3.Li, J.: Research of the Method in the Infrared Images Recognition. Doctoral Dissertation of National University of Defense Technology (2005)Google Scholar
- 4.Wilde, J., Phillips, P., Jiang, C., Wiener, S.: Comparison of Visible and Infra-Red Imagery for Face Recognition. In: International Conference on Automatic Face and Gesture Recognition, pp. 182–187 (1996)Google Scholar
- 5.Prokoski, F., Riedel, R., Coffin, J.: Identification of Individuals by Means of Facial Thermography. In: IEEE International Carnahan Conference on Security Technology, pp. 120–125 (1992)Google Scholar
- 6.Selinger, A., Socolinsky, D.: Appearance-based Facial Recognition Using Visible and Thermal Imagery: a Comparative Study. Technical Report 02-01, Equinox Corporation (2002)Google Scholar
- 7.Wolff, L., Socolinsky, D., Eveland, C.: Faces Recognition in the Thermal Infrared. Equinox Corporation 43(2), 134–144 (2004)Google Scholar
- 8.Fan, C., Wang, S., Zhang, F.: Wavelet-based Illumination Normalization Algorithm for Face Recognition. Computer Engineering and Applications 46(6), 174–177 (2010)Google Scholar
- 9.Ju, S., Zhou, J.: Face Recognition Based on Illumination Normalization in Frequency-Domain. The Transaction of University Electronic Science and Technology of China 38(6), 1021–1025 (2009)Google Scholar
- 10.Liu, H., Li, J., Jun, M.: Illumination Compensation Based on Multi-method Integration. Journal of System Simulation 13(3), 486–490 (2001)Google Scholar
- 11.Wu, S.Q., Jiang, L.J., Xie, S.L.: Infrared Face Recognition by Using Blood Perfusion Data Proceeding of Audio and Video based Biometric Person Authentication, pp. 320–328 (2005)Google Scholar
- 12.Socolinsky, D., Selinger, A.: Comparative Analysis of Face Recognition Performance with Visible and Thermal Infrared Imagery. In: Proceeding of the International Conference on Pattern Recognition, pp. 124–133 (2002)Google Scholar