Abstract
L1-norm based dimensionality reduction methods are the most effective techniques in computer vision and pattern recognition. However, they emphasize the robustness to outliers too much and overlook the correlation information among data so that they usually encounter the instability problem. To overcome this problem, in this paper, we propose a method called L1-norm and trace Lasso based locality correlation projection (L1/TL-LRP), in which the robustness, sparsity, and correlation are jointly considered. Specifically, by introducing the trace Lasso regularization, L1/TL-LRP is adaptive to the correlation structure that benefits from both L2-norm and L1-norm. Besides, an effective procedure based on Alternating Direction Method of Multipliers is proposed for solving L1/TL-LRP. Finally, we conduct extensive experiments on several databases for data classification. The inspiring experimental results demonstrate the effectiveness of the proposed method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Paul, A., Chaki, N.: Dimensionality reduction of hyperspectral images using pooling. Pattern Recogn. Image Anal. 29(1), 72–78 (2019). https://doi.org/10.1134/S1054661819010085
De Bodt, C., Mulders, D., Verleysen, M., et al.: Nonlinear dimensionality reduction with missing data using parametric multiple imputations. IEEE Trans. Neural Netw. Learn. Syst. 30(4), 1166–1179 (2019)
Yuan, S., Mao, X., Chen, L.: Multilinear spatial discriminant analysis for dimensionality reduction. Image Process. IEEE Trans. 26(6), 2669–2681 (2017)
Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71–86 (1991)
Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 711–720 (1997)
He, X., Yan, S., Hu, Y., Niyogi, P., Zhang, H.-J.: Face recognition using Laplacianfaces. IEEE Trans. Pattern Anal. Mach. Intell. 27(3), 328–340 (2005)
He, X.F., Cai, D., Yan, S., Zhang, H.J.: Neighborhood preserving embedding. In: The 10th IEEE International Conference on Computer Vision (ICCV), vol. 2, pp. 1208–1213 (2005)
Zhang, D., He, J., Zhao, Y., Luo, Z., Du, M.: Global plus local: a complete framework for feature extraction and recognition. Pattern Recogn. 47(3), 1433–1442 (2014)
Yang, J., Zhang, D., Yang, J., Niu, B.: Globally maximizing, locally minimizing: unsupervised discriminant projection with applications to face and palm biometrics. IEEE Trans. Pattern Anal. Mach. Intell. 29(4), 650–664 (2007)
Zang, F., Zhang, J., Pan, J.: Face recognition using elasticfaces. Pattern Recogn. 45(11), 3866–3876 (2012)
Yuan, S., Mao, X.: Exponential elastic preserving projections for facial expression recognition. Neurocomputing 275, 711–724 (2018)
Wang, H., Lu, X., Hu, Z., Zheng, W.: Fisher discriminant analysis with L1-norm. IEEE Trans. Cyber. 44(6), 828–842 (2014)
Kwak, N.: Principal component analysis based on L1-norm maximization. IEEE Trans. Pattern Anal. Mach. Intell. 30(9), 1672–1680 (2008)
Nie, F., Huang, H., Ding, C., Luo, D., Wang, H.: Robust principal component analysis with non-greedy L1-norm maximization. In: Proceedings of the 22nd International Joint Conference on Artificial Intelligence (IJCAI), pp. 1433–1438. Barcelona (2011)
Zhong, F., Zhang, J.: Linear discriminant analysis based on L1-norm maximization. IEEE Trans. Image Process. 22(8), 3018–3027 (2013)
Pang, Y., Yuan, Y.: Outlier-resisting graph embedding. Neurocomputing 73(4), 968–974 (2010)
Zhong, F., Zhang, J., Li, D.: Discriminant locality preserving projections based on L1-norm maximization. IEEE Trans. Neural Netw. Learn. Syst. 25(11), 2065–2074 (2014)
Meng, D., Zhao, Q., Xu, Z.: Improve robustness of sparse PCA by L1-norm maximization. Pattern Recogn. 45(1), 487–497 (2012)
Grave, E., Obozinski, G., Bach, F.: Trace Lasso: a trace norm regularization for correlated designs. Adv. Neural Inf. Process. Syst. 2187–2195 (2011)
Lu, G.F., Zou, J., Wang, Y., Wang, Z.: L1-norm-based principal component analysis with adaptive regularization. Pattern Recogn. 60(C), 901–907 (2016)
Wang, J., Lu, C., Wang, M., Li, P., Yan, S., Hu, X.: Robust face recognition via adaptive sparse representation. IEEE Trans. Cybern. 44(12), 2368–2378 (2014)
Lin, Z., Chen, M., Ma, Y.: The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices. UIUC Technical Report, UILU-ENG-09–2215 (2009)
Cai, J.-F., Candès, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2010)
Donoho, D.L.: For most large underdetermined systems of linear equations the minimal L1-norm solution is also the sparsest solution. Commun. Appl. Math. 59(6), 797–829 (2006)
Hinton, G.E.: Visualizing high-dimensional data using t-SNE. J. Mach. Learn. Res. 9(2), 2579–2605 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yuan, S., Chen, S., Zhang, F., Huang, W. (2021). L1-Norm and Trace Lasso Based Locality Correlation Projection. In: Sun, F., Liu, H., Fang, B. (eds) Cognitive Systems and Signal Processing. ICCSIP 2020. Communications in Computer and Information Science, vol 1397. Springer, Singapore. https://doi.org/10.1007/978-981-16-2336-3_6
Download citation
DOI: https://doi.org/10.1007/978-981-16-2336-3_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2335-6
Online ISBN: 978-981-16-2336-3
eBook Packages: Computer ScienceComputer Science (R0)