A Wavelet-Based Image Preprocessing Method or Illumination Insensitive Face Recognition

In this paper, we propose a wavelet-based illumination normalization method for face recognition against different directions and strength of light. Here, by one-level discrete wavelet transform, a given face image is first decomposed into low frequency and high frequency components, respectively, and then the two components are processed separately through contrast enhancement to eliminate the effect of illumination variations and enhance the detailed edge information. Finally the normalized image is obtained through the inverse discrete wavelet transform. Experimental results on the Yale B, the extended Yale B and CMU PIE face databases show that the proposed method can effectively reduce the effect of illumination variations on face recognition.