Sparse two-dimensional discriminant locality-preserving projection (S2DDLPP) for feature extraction
- 99 Downloads
Two-dimensional locality-preserving projection (2DLPP) is an unsupervised method, so it can’t use the discrimination information of the sample in the sparse data; elastic net regression can obtain a sparse results of the feature extraction. So, this paper presents a new method for image feature extraction, namely the sparse two-dimensional discriminant locality-preserving projection (S2DDLPP) based on the 2D discriminant locality-preserving projection (2DDLPP) and elastic net regression. By adding the between-class scatter and discrimination information into the objective function of 2DLPP, S2DDLPP uses elastic net regression to obtain an optimal sparse projection matrix with “minimizing the within-class scatter” and “maximizing the between-class scatter.” Compared with other methods (2DPCA, 2DPCA-L1, 2DLDA, 2DLPP, 2DDLPP, and 2DDLPP-L1), the experimental results on the ORL, Yale, AR and FERET face database show the effectiveness of the proposed algorithm.
KeywordsTwo-dimensional locality preserving projection Elastic net regression Sparsity Feature extraction Discrimination information
This work is partially supported by National Key R&D Program Grant No. 2017YFC0804002, the National Science Foundation of China under Grant Nos. 61462064, 6177227, 61362031, 61463008, 61403188, 61503195, 61603192, and the China Postdoctoral Science Foundation under Grant No. 2016M600674, the Natural Science Fund of Jiangsu Province under Grants BK20161580, BK20171494 and China’s Aviation Science (No. 20145556011).
Compliance with ethical standards
Conflict of interest
There are no conflicts of interest.
- Li X, Pang Y, Yuan Y (2009) L1-norm-based 2DPCA. IEEE Trans Syst Man Cybern B Cybern 40(4):1170–1175Google Scholar
- Nie F, Yuan J, Huang H (2014) Optimal mean robust principal component analysis. In: Proceedings of the international conference on international conference on machine learning, pp 1062–1070Google Scholar
- Nie F, Zhu W, Li X (2017) Unsupervised large graph embedding. In: Proceedings of 31st AAAI conference on artificial intelligence, San Francisco, CA, pp 2422–2428Google Scholar
- Song Y (2009) Orthogonal locality minimizing globality maximizing projections for feature extraction. Opt Eng 48(1):017202–017202-5Google Scholar
- Tang Y, Zhang Z, Zhang Y, Li F (2016) Robust L1-norm matrixed locality preserving projection for discriminative subspace learning. In: Proceedings of international joint conference on neural networks, pp 4199–4204Google Scholar
- Zhao HX, Xing HJ, Wang XZ, Chen JF(2011) L1-norm-based 2DLPP. In: Proceedings of Chinese conference on control and decision, pp 1259–1264Google Scholar