Abstract
This paper presents a new method for improving face recognition performance under difficult conditions. Specifically, a new image representation scheme is proposed which is derived from the YCrQ colour space using principal component analysis (PCA) followed by Fisher linear discriminant analysis (FLDA). A multi-scale local feature, LBP-DWT, is used for face representation which is computed by extracting different resolution local binary patterns (LBP) features from the new image representation and transforming the LBP features into the wavelet domain using discrete wavelet transform (DWT) and Haar wavelets. A variant of non-parametric discriminant analysis (NDA), called regularised non-parametric discriminant analysis (RNDA) is introduced to extract the most discriminating features from LBP-DWT. The proposed methodology has been evaluated using two challenging face databases (FERET and multi-PIE). The promising experimental results show that the proposed method outperforms two state-of-the-art methods, one based on Gabor features and the other based on sparse representation classification (SRC).