Multi-Features Fusion Based Face Recognition

In order to accelerate data processing and improve classification accuracy, some classic dimension reduction techniques have been proposed in the past few decades, such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Non-negative Matrix Factorization (NMF), etc. However, these methods only use single feature and do not consider multi-features. In this paper, for the sake of exploiting the complementarity between multiple features, we put forward an efficient data dimensionality reduction scheme based on multi-features fusion. Specifically, gray value and local binary pattern features of all images are first extracted, and then some representative dimension reduction methods are applied. A series of experimental results are carried out on two benchmark face data sets to demonstrate the effectiveness of our proposed scheme.