JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering 2016 Vol.17 No.3 P.212-223

Local uncorrelated local discriminant embedding for face recognition

Author(s): Xiao-hu Ma, Meng Yang, Zhao Zhang
Affiliation(s): School of Computer Science and Technology, Soochow University, Suzhou 215006, China; more
Corresponding email(s): xhma@suda.edu.cn, eyangmeng@163.com, cszzhang@suda.edu.cn
Key Words: Feature extraction, Local discriminant embedding, Local uncorrelated criterion, Face recognition

Share this article to： More <<< Previous Article \|Next Article >>>

Abstract: The feature extraction algorithm plays an important role in face recognition. However, the extracted features also have overlapping discriminant information. A property of the statistical uncorrelated criterion is that it eliminates the redundancy among the extracted discriminant features, while many algorithms generally ignore this property. In this paper, we introduce a novel feature extraction method called local uncorrelated local discriminant embedding (LULDE). The proposed approach can be seen as an extension of a local discriminant embedding (LDE) framework in three ways. First, a new local statistical uncorrelated criterion is proposed, which effectively captures the local information of interclass and intraclass. Second, we reconstruct the affinity matrices of an intrinsic graph and a penalty graph, which are mentioned in LDE to enhance the discriminant property. Finally, it overcomes the small-sample-size problem without using principal component analysis to preprocess the original data, which avoids losing some discriminant information. Experimental results on Yale, ORL, Extended Yale B, and FERET databases demonstrate that LULDE outperforms LDE and other representative uncorrelated feature extraction methods.

局部不相关的局部判别嵌入人脸识别算法

目的：统计不相关是一种重要的性质，然而一些人脸识别算法常将这一性质忽略。统计不相关准则目的是使得特征线性不相关，消除提取的判别特征之间的冗余信息。已有的一些算法只是分别考虑数据集的全局统计不相关特征和数据集的局部的不相关特性。为解决这一问题，本文提出一种新的特征提取算法—局部不相关的局部判别嵌入算法（local uncorrelated local discriminant embedding，LULDE），该算法能同时考虑数据集中的同类和异类样本点的局部信息。
创新点：该算法有三点贡献：（1）提出了一种新的局部不相关准则，能同时利用数据集中的同类和异类样本点的局部信息；（2）重新构造局部判别嵌入算法中的本征图G和惩罚图G_P对应的邻接矩阵，使得算法比原有的局部判别嵌入算法具有更强的判别能力；（3）利用一种不同于PCA预处理的方式解决了“小样本”问题。
方法：首先，重新定义本征图的邻接矩阵W和惩罚图的邻接矩阵W_P。然后确定LULDE算法的目标函数。最后，通过求解特征值问题得到最优投影矩阵。
结论：在Yale，ORL，Extended Yale B和FERET四个常用人脸数据库上的大量实验结果表明了本算法的有效性。

关键词：特征提取；局部判别嵌入；局部不相关准则；人脸识别

Reference

[1]Belhumeur, P.N., Hespanha, J.P., Kriegman, D., 1997. Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE Trans. Patt. Anal. Mach. Intell., 19(7):711-720.

[2]Belkin, M., Niyogi, P., 2003. Laplacian eigenmaps for dimensionality reduction and data representation. Neur. Comput., 15(6):1373-1396.

[3]Chen, H.T., Chang, H.W., Liu, T.L., 2005. Local discriminant embedding and its variants. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, p.846-853.

[4]Chen, Y., Zheng, W.S., Xu, X.H., et al., 2013. Discriminant subspace learning constrained by locally statistical uncorrelation for face recognition. Neur. Netw., 42:28-43.

[5]Fan, Z.Z., Xu, Y., Zhang, D., 2011. Local linear discriminant analysis framework using sample neighbors. IEEE Trans. Neur. Netw., 22(7):1119-1132.

[6]He, X.F., Niyogi, P., 2003. Locality preserving projections. Proc. Advances in Neural Information Processing Systems, p.327-334.

[7]Jin, Z., Yang, J.Y., Hu, Z.S., et al., 2001. Face recognition based on the uncorrelated discriminant transformation. Patt. Recog., 34(7):1405-1416.

[8]Jing, X.Y., Zhang, D., Jin, Z., 2003. UODV: improved algorithm and generalized theory. Patt. Recog., 36(11):2593-2602.

[9]Jing, X.Y., Li, S., Zhang, D., et al., 2011. Face recognition based on local uncorrelated and weighted global uncorrelated discriminant transforms. Proc. 18th IEEE Int. Conf. on Image Processing, p.3049-3052.

[10]Roweis, S.T., Saul, L.K., 2000. Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500):2323-2326.

[11]Tenenbaum, J.B., de Silva, V., Langford, J.C., 2000. A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500):2319-2323.

[12]Turk, M., Pentland, A., 1991. Eigenfaces for recognition. J. Cogn. Neurosci., 3(1):71-86.

[13]Wong, W.K., Zhao, H.T., 2012. Supervised optimal locality preserving projection. Patt. Recog., 45(1):186-197.

[14]Yan, S.C., Xu, D., Zhang, B.Y., et al., 2007. Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans. Patt. Anal. Mach. Intell., 29(1):40-51.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Similar articles

- Go to

局部不相关的局部判别嵌入人脸识别算法

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference