A Deep Graph Embedding Network Model for Face Recognition
This is an incremental improvement for face recognition systems.
The authors tackled face recognition by proposing GENet, a deep learning network combining multi-layer architecture with graph embedding, achieving higher classification accuracy on CMU-PIE, ORL, and Extended Yale B datasets.
In this paper, we propose a new deep learning network "GENet", it combines the multi-layer network architec- ture and graph embedding framework. Firstly, we use simplest unsupervised learning PCA/LDA as first layer to generate the low- level feature. Secondly, many cascaded dimensionality reduction layers based on graph embedding framework are applied to GENet. Finally, a linear SVM classifier is used to classify dimension-reduced features. The experiments indicate that higher classification accuracy can be obtained by this algorithm on the CMU-PIE, ORL, Extended Yale B dataset.