Advanced Hybrid Color Space Normalization for Human Face Extraction and Detection

This paper presents a new color space normalization (CSN) technique for enhancing the discriminating power of color space along with the principal component analysis (PCA) for the face recognition process. The common RGB technique is not suitable for the characterizing of the skin color due to the presence of luminance factor. In the YCbCr color space, the luminance information is contained in Y component, and the chrominance information is in Cb and Cr. Therefore, the luminance information can be easily de-embedded. Different color spaces have different discriminating power, in this paper, eye can be perfectly detected by using YcbCr color space and the mouth regions can be perfectly detected by using the YIQ color space. Then PCA is used to express the large 1-D vector of pixels constructed from 2-D facial image into the compact principal components of the feature space. Each face image may be represented as a weighted sum (feature vector) of the eigenfaces, which are stored in a 1D array. PCA allows us to compute a linear transformation that maps data from a high dimensional space to a lower dimensional space. It covers standard deviation, covariance, eigenvectors and eigenvalues. Face recognition is obtained by PCA without much loss of information. Experiments using different databases by varying the facial expressions (open/closed eyes, smiling/not smiling) show that the proposed method by combining color space discrimination and PCA can improve face recognition to a great extend.