| Summary: | Face recognition has a great potential to play an important role in computer vision field. However, the majority of face recognition methods are based on the low-level features, which may not yield good results. Inspired by a simple deep learning model principal component analysis network (PCANet), we propose a novel deep learning network called circular symmetrical Gabor filter (2D)<sup>2</sup>PCA neural networks [CSGF(2D)<sup>2</sup>PCANet]. Previous models used in face recognition have three major issues of data redundancy, computation time, and no rotation invariance. We introduce the CSGF to address these issues. Two-directional 2-D PCA [(2D)<sup>2</sup>PCA] is used in feature extraction stage. Binary hashing, blockwise histograms, and linear SVM are used for the output stage. The proposed CSGF (2D)<sup>2</sup>PCANet learns highlevel features and provides more recognition information during the training phase, which may result in a higher recognition rate when testing the sample. We tested the proposed method on XM2VTS, ORL, AR, Extend Yale B, and LFW databases. Test results show that the CSGF (2D)<sup>2</sup>PCANet is more robust to the variation of occlusion, illumination, pose, noise, and expression, which is a promising method in face recognition.
|
|---|
