A deep architecture for face recognition based on multiple feature extraction techniques

Some of the best current face recognition approaches use feature extraction techniques based on either Principle Component Analysis (PCA), Local Binary Patterns (LBP), Autoencoder (non-linear PCA), etc. While each of these feature techniques works fairly well, we propose to combine multiple feature extractors with deep learning in a system so that the overall face recognition accuracy can be improved. The output from multiple feature extractions is classified using a deep learning approach. Deep learning algorithms possess high capability to learn more complex functions in order to handle difficult computer vison tasks. Our proposed method integrates the output of three different feature extractors, specifically PCA, LBP+PCA, and dimensionality reduction of LBP features using a Neural Network (NN). The features from the above three techniques are concatenated to form a joint feature vector. This feature vector is fed into a deep Sacked Sparse Autoencoder (SSA) as a classifier to generate the recognition results. Our proposed approach is evaluated by ORL and AR face databases. The experimental results indicate that our system outperforms existing ones based on individual feature techniques as well as reported systems employing multiple feature types.