Face Recognition Based on PCA and SVM
Xianwei Li, Guolong Chen · 2012
PCA is a well-known feature extraction and data representation technique widely used in the areas of pattern recognition, computer vision and signal processing, etc. But this method is usually affected by light illumination. A novel technique for face recognition is presented in this paper. PCA and SVM are combined in this technique. Before using PCA to extract feature, these images should be processed by wavelet transform. In recognition stage, support vector machine (SVM) is adopted as classifiers. Experiments based on Cambridge ORL face database indicated that our approach can achieve better performance than use PCA only.