Abstract
Classical subspace learning methods such as spectral regression (SR) and its sparse extensions are all two-step ways, which will lead to a suboptimal subspace for feature extraction. Another potential drawback is that these methods are not robust to the outliers and the variations of data because they use Frobenius norm as the basic distance metric. To address these problems, a novel face recognition method called robust embedding regression (RER) is proposed, which performs low-dimensional embedding and jointly sparse regression simultaneously. By this way, the optimal subspace can be obtained. Besides, we not only emphasize \( L_{2,1} \)-norm minimization on both loss function and regularization terms, but also use \( L_{2,1} \)-norm as the basic distance metric. Therefore, we can obtain jointly sparse projections in the regression process and more stable and robust low-dimensional reconstruction in the embedding process. Moreover, we use a more generalized constraint to improve the generalization of RER. The corresponding optimal solution can be computed by generalized eigen-decomposition via an iterative optimization algorithm. Theoretical analysis and experimental results prove the convergence of RER. Extensive experiments show the proposed RER has a better performance than other related methods on four well-known datasets.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71–86 (1991)
Belhumeur, P., Hespanha, J., Kriengman, D.: 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.: Face recognition using Laplacianfaces. IEEE Trans. Pattern Anal. Mach. Intell. 27(3), 328–340 (2005)
He, X., Cai, D., Yan, S., Zhang, H.: Neighborhood preserving embedding. In: 10th IEEE International Conference on Computer Vision, pp. 1208–1213 (2005)
Yan, S., Xu, D., Zhang, B., Zhang, H., Yang, Q., Lin, S.: Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans. Pattern Anal. Mach. Intell. 29(1), 40–51 (2007)
Cai, D., He, X., Han, J.: Spectral regression for efficient regularized subspace learning. In: 11th International Conference on Computer Vision, pp. 1–8 (2007)
Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. R. Stat. Soc. Ser. B 67(2), 301–320 (2005)
Zou, H., Hastie, T., Tibshirani, R.: Sparse principal component analysis. J. Comput. Graph Stat. 15(2), 265–286 (2006)
Clemmensen, L., Hastie, T., Witten, D., Ersbøll, B.: Sparse discriminant analysis. Technometrics 53(4), 406–413 (2011)
Lai, Z., Wong, W., Xu, Y., Yang, J., Zhang, D.: Approximate orthogonal sparse embedding for dimensionality reduction. IEEE Trans. Neural Netw. Learn. Syst. 27(4), 723–735 (2016)
Cai, D., He, X., Han, J.: Spectral regression: a unified approach for sparse subspace learning. In: 7th IEEE International Conference on Data Mining, pp. 73–82 (2007)
Gu, Q., Li, Z., Han, J.: Joint feature selection and subspace learning. In: International Joint Conference on Artificial Intelligence, pp. 1294–1299 (2011)
Nie, F., Huang, H., Cai, X., Chris, D.: Efficient and robust feature selection via joint L2,1 norms minimization. In: 23th Neural Information Processing Systems, pp 1813–1821 (2010)
Zheng, Z., Lei, W., Huan, L.: Efficient spectral feature selection with minimum redundancy. In: 24th AAAI Conference on Artificial Intelligent, pp 1–6 (2010)
Liu, X., Wang, L., Zhang, J., Yin, J., Liu, H.: Global and local structure preservation for feature selection. IEEE Trans. Neural Netw. Learn. Syst. 25(6), 1083–1095 (2014)
Hou, C., Nie, F., Li, X., Yi, D., Wu, Y.: Joint embedding learning and sparse regression: a framework for unsupervised feature selection. IEEE Trans. Cybern. 44(6), 793–804 (2014)
Lai, Z., Mo, D., Wong, W., Xu, Y., Miao, D., Zhang, D.: Robust discriminant regression for feature extraction. IEEE Trans. Cybern. 48(8), 2472–2484 (2018)
Chen, Y., Lai, Z., Wong, W., Shen, L., Hu, Q.: Low-rank linear embedding for image recognition. IEEE Trans. Multimed. 20(12), 3212–3222 (2018)
Lai, Z., Mo, D., Wen, J., Shen, L., Wong, W.: Generalized robust regression for jointly sparse subspace learning. IEEE Trans. Circuits Syst. Video Technol. 29(3), 756–772 (2019)
Nie, F., Huang, H., Cai, X., Ding, C.: Efficient and robust feature selection via joint ℓ2, 1-norms minimization. In: Neural Information Processing Systems (2010)
Yang, Y., Shen, H., Ma, Z., Huang, Z., Zhou, X.: L2,1-norm regularized discriminative feature selection for unsupervised learning. In: International Joint Conference on Artificial Intelligence (2011)
Lai, Z., Xu, Y., Yang, J., Shen, L., Zhang, D.: Rotational invariant dimensionality reduction algorithms. IEEE Trans. Cybern. 47(11), 3733–3746 (2017)
Li, X., Zhang, H., Zhang, R., Liu, Y., Nie, F.: Generalized uncorrelated regression with adaptive graph for unsupervised feature selection. IEEE Trans. Neural Netw. Learn. Syst. 30, 1–9 (2018)
Acknowledgments
This work was supported in part by the Natural Science Foundation of China under Grant 61573248, Grant 61802267 and Grant 61732011, and in part by the Shenzhen Municipal Science and Technology Innovation Council under Grant JCYJ20180305124834854 and JCYJ20160429182058044, in part by the Natural Science Foundation of Guangdong Province (Grant 2017A030313367 and Grant 2016114162135515).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Bao, J., Lu, J., Lai, Z., Liu, N., Lu, Y. (2019). Robust Embedding Regression for Face Recognition. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2019. Lecture Notes in Computer Science(), vol 11858. Springer, Cham. https://doi.org/10.1007/978-3-030-31723-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-31723-2_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31722-5
Online ISBN: 978-3-030-31723-2
eBook Packages: Computer ScienceComputer Science (R0)