LPPNet: A Learning Network for Image Feature Extraction and Classification

PCANet is a very simple learning network for image classification. Inspired by PCANet, we propose a new learning network, referred to as LPPNet, for image feature extraction and classification. Different from PCANet, LPPNet takes the class information and the local geometric structure of data into account simultaneously. In LPPNet, local preserving projections (LPP) is first employed to learn filters, and then binary hashing and block histograms are used for indexing and pooling. Experimental results on several image datasets verify the effectiveness and robustness of LPPNet for image feature extraction and classification.