Abstract
Linear discriminant analysis (LDA) is one of the most popular feature extraction methods in image recognition. Nevertheless, LDA always suffers from some undesired behaviors caused by globality, namely ignoring local geometric structure of images. To fully capture the geometric information, we propose a novel two-dimensional linear discriminant analysis with locality preserving (2DLP-LDA) approach, which can cover both within-class and between-class local geometric information. 2DLP-LDA re-characterizes the within-class scatter matrix by employing locality preserving projection technique and re-characterizes the between-class scatter matrix by introducing a Gaussian weighting function, making the samples from the same class moderately cluster, while the samples from different classes properly distribute in the reduced subspace. Encouraging experimental results on FERET face database as well as SEU bovine iris database show the effectiveness of the proposed approach.
Similar content being viewed by others
References
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)
Bartlett, M.S., Movellan, J.R., Sejnowski, T.J.: Face recognition by independent component analysis. IEEE Trans. Neural Netw. 13(6), 1450–1464 (2002)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05). IEEE 1, 886–893 (2005)
Ojala, T., Pietikäinen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recogn. 29(1), 51–59 (1996)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)
Krizhevsky, A, Sutskever, I, Hinton, G E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems. pp. 1097–1105 (2012)
de Alcantara, M. F., et al.: Action identification using a descriptor with autonomous fragments in a multilevel prediction scheme. In: Signal, Image and Video Processing, pp. 1–8 (2016)
Jia, B., Feng, W., Zhu, M.: Obstacle detection in single images with deep neural networks. SIViP 10(6), 1033–1040 (2016)
Li, J., Zou, L., Yan, J., et al.: No-reference image quality assessment using Prewitt magnitude based on convolutional neural networks. SIViP 10(4), 609–616 (2016)
Loog, M., Duin, R.P.W., Haeb-Umbach, R.: Multiclass linear dimension reduction by weighted pairwise Fisher criteria. IEEE Trans. Pattern Anal. Mach. Intell. 7, 762–766 (2001)
Zhi, R., Ruan, Q.: Two-dimensional direct and weighted linear discriminant analysis for face recognition. Neurocomputing 71(16), 3607–3611 (2008)
Chen, F., An, S., Liu, W.: A new face recognition approach to boosting the worst-case performance. Advances in Multimedia Information Processing-PCM 2008. Springer, Berlin (2008)
Lu, C., An, S., Liu, W., et al.: An innovative weighted 2DLDA approach for face recognition. J. Signal Process. Syst. 65(1), 81–87 (2011)
Gao, Q.X., Xu, H., Li, Y.Y., et al.: Two-dimensional supervised local similarity and diversity projection. Pattern Recogn. 43(10), 3359–3363 (2010)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Tenenbaum, J.B., De Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319–2323 (2000)
Niyogi, X.: Locality preserving projections. Neural Information Processing Systems, p. 153. MIT, Cambridge (2004)
Yu, W., Teng, X., Liu, C.: Face recognition using discriminant locality preserving projections. Image Vis. Comput. 24(3), 239–248 (2006)
Sugiyama, M.: Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis[J]. J. Mach. Learn. Res. 8, 1027–1061 (2007)
Zhang, D., Yang, J., Yang, J., et al.: Globally maximizing, locally minimizing: unsupervised discriminant projection with applications to face and palm biometrics[J]. IEEE Trans. Pattern Anal. Mach. Intell. 29(4), 650–664 (2007)
Shu, X., Gao, Y., Lu, H.: Efficient linear discriminant analysis with locality preserving for face recognition. Pattern Recogn. 45(5), 1892–1898 (2012)
Gao, Q., Liu, J., Zhang, H., et al.: Enhanced fisher discriminant criterion for image recognition. Pattern Recogn. 45(10), 3717–3724 (2012)
Zhang, D., He, J., Zhao, Y., et al.: Global plus local: a complete framework for feature extraction and recognition. Pattern Recogn. 47(3), 1433–1442 (2014)
Fukunaga, K.: Introduction to Statistical Pattern Recognition, vol. 9, pp. 401–405. Academic Press, Cambridge (1990)
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)
Chen, L.F., Liao, H.Y.M., Ko, M.T., et al.: A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recogn. 33(10), 1713–1726 (2000)
Yu, H., Yang, J.: A direct LDA algorithm for high-dimensional data—with application to face recognition. Pattern Recogn. 34(10), 2067–2070 (2001)
Song, F., Zhang, D., Wang, J., et al.: A parameterized direct LDA and its application to face recognition. Neurocomputing 71(1), 191–196 (2007)
Kong, H., Teoh, E.K., Wang J.G., et al.: Two dimensional fisher discriminant analysis: Forget about small sample size problem. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005 (ICASSP’05). IEEE. 2: 761–764 (2005)
Noushath, S., Kumar, G.H., Shivakumara, P.: (2D) 2 LDA: An efficient approach for face recognition. Pattern Recogn. 39(7), 1396–1400 (2006)
Kong, H., Wang, L., Teoh, E.K.: A framework of 2D Fisher discriminant analysis: application to face recognition with small number of training samples. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2005, CVPR 2005. IEEE 2, 1083–1088 (2005)
Zheng, W.S., Lai, J.H., Li, S.Z.: 1D-LDA vs. 2D-LDA: When is vector-based linear discriminant analysis better than matrix-based? Pattern Recogn. 41(7), 2156–2172 (2008)
Hu, D., Feng, G., Zhou, Z.: Two-dimensional locality preserving projections (2DLPP) with its application to palmprint recognition. Pattern Recogn. 40(1), 339–342 (2007)
Weiwei, Y.: Two-dimensional discriminant locality preserving projections for face recognition. Pattern Recogn. Lett. 30(15), 1378–1383 (2009)
Wong, W.K., Zhao, H.T.: Supervised optimal locality preserving projection. Pattern Recogn. 45(1), 186–197 (2012)
Li, M., Yuan, B.: 2D-LDA: a statistical linear discriminant analysis for image matrix. Pattern Recogn. Lett. 26(5), 527–532 (2005)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (No. 71390333), the National Key Technology R&D Program of China during the 12th Five-Year Plan Period (No. 2013BAD19B05) and the Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYZZ15_0072).
Author information
Authors and Affiliations
Corresponding author
Appendix: Proof of rewriting \(S_{B}\)
Appendix: Proof of rewriting \(S_{B}\)
It follows from \(S_B =\sum _i^C {M_i (\bar{{A}}^{i}-\bar{{A}})^{T}(\bar{{A}}^{i}-\bar{{A}})} \) that
which yields Eq. (5).
Rights and permissions
About this article
Cite this article
Wei, Z., Chu, Y. & Zhao, L. An effective two-dimensional linear discriminant analysis with locality preserving approach for image recognition. SIViP 11, 1577–1584 (2017). https://doi.org/10.1007/s11760-017-1122-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-017-1122-7