Two Adaptive Image Pre-processing Chains for Face Recognition Rate Enhancement

In this paper, two adaptive image enhancement and de-noising chains are produced. Our aim is to enhance the face image quality that stored in a large database for face recognition applications. Each processing chain consists of three steps, the first chain is proposed to enhance Principal Component Analysis (PCA) and Kernel Principal Component Analysis (KPCA) recognition rate, in the first step of this chain, the face images are de-noised with Haar wavelet de-noising filter at level ten of decomposition, in the second step, the de-noised image is adjusted to enhance the image contrast, and in the third step the high pass filter ‘Laplacian of Gaussian filter ’ is used for detecting edges in face images. The second chain is proposed to enhance Linear Discriminat Analysis LDA and Kernel Fisher Analysis (KFA) recognition rate, in the first step of this chain the image contrast is adjusted and entered to histogram equalization as second step and in the third step the image is de-noised with Haar wavelet de-noising filter at level ten of decomposition. Our approaches produced good result and contributed in raising the recognition rate in PCA, KPCA, LDA and KFA up to 10%, 20%, 5 % and 4 % respectively when 400 face images are used