摘要：A novel Gabor-based Improved Supervised Locality Preserving Projections for face recognition is presented in this paper. This new algorithm is based on a combination of Gabor wavelets representation of face images and Improved Supervised Locality Preserving Projections for face recognition and it is robust to changes in illumination and facial expressions and poses. In this paper, Gabor filter is first designed to extract the features from the whole face images, and then a supervised locality preserving projections, which is improved by two-directional 2DPCA to eliminate redundancy among Gabor features, is used to augment these Gabor feature vectors derived from Gabor wavelets representation. The new algorithm benefits mostly from two aspects: One aspect is that Gabor wavelets are promoted for their useful properties, such as invariance to illumination, rotation, scale and translations, in feature extraction. The other is that the Improved Supervised Locality Preserving Projections not only provides a category label for each class in a training set, but also reduces more coefficients for image representation from two directions and boost the recognition speed. Experiments based on the ORL face database demonstrate the effectiveness and efficiency of the new method. Results show that our new algorithm outperforms the other popular approaches reported in the literature and achieves a much higher accurate recognition rate.
