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.
KeywordsLPPNet Learning network Feature extraction Image classification
This work is supported in part by the NSFC-Henan Talent Jointly Training Foundation of China (no. U1504621) and the Key Scientific Research Project of University in Henan Province of China (no. 18A120001).
- 4.Tenenbaum, J.B., Silva, V.d., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319–2323 (2000)Google Scholar
- 12.Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression database. IEEE Trans. Pattern Anal. Mach. Intell. 25(12), 1615–1618 (2010)Google Scholar