Histogram-enhanced principal component analysis for face recognition

In this paper we present an enhanced principal component analysis (PCA) algorithm for improving the rate of face recognition. The proposed method modifies the image histogram to provide a Gaussian shaped tonal distribution in the face images, such that spatially the entire set of face images presents similar facial gray-level intensities while the face content in the frequency domain remains mostly unaltered. Computationally inexpensive, the algorithm proves to yield superior results when applied as a preprocessing step for face recognition. Experimental results are presented to demonstrate effectiveness of the proposed technique.