Infrared Face Recognition Method Based on Radiative Energy and Block-PCA

A novel method for infrared face recognition based on radiative energy is proposed in this paper. To reduce the influence of environmental temperature, the raw thermal images are transformed to the radiative energy images by Stefan-Boltzmann Law. Block-PCA instead of whole PCA is utilized to get the local discrimination information, which can solve the small sample size problem (the null space problem). Then, a weighted algorithm is applied to form the holistic features. Finally, The FLD is applied to the holistic features combined by the extracted coefficients from the information of all sub-blocks. The experiments illustrate that the method proposed has better performance compared with traditional methods.