结合半监督学习中的自学习技术以及二维主成分分析(two-dimensional principal componentanalysis-2DPCA)方法,提出了一种基于半监督学习的人脸识别方法.在二维主成分分析的基础上,利用少量具有类别标签的样本训练分类器,然后利用半监督学习中的自学习技术,对未知类别标签的人脸样本进行分类,并将具有高置信度的人脸样本加入到训练集中,以此增加训练集中的人脸样本数量.在ORL人脸库和Yale人脸库的实验结果,表明了提出方法的有效性.
[1] 曾岳, 冯大政, Zeng Yue, Feng Da-zheng. 一种基于加权变形的2DPCA的人脸特征提取方法 [J]. 电子与信息学报 2011.doi:10.3724/SP.J.1146.2010.01003
[2] TURK M A, PENTLAND A P. Face recognition using eigenfaces [A]. Maui, HI 1991.
[3] Keun-Chang Kwak, Witold Pedrycz. Face Recognition Using an Enhanced Independent Component Analysis Approach [J]. IEEE Transactions on Neural Networks 2007, 2(2).
[4] Jian Yang, Zhang D., Frangi A.F., Jing-yu Yang. Two-dimensional PCA: a new approach to appearance-based face representation and recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence 2004, 1(1).
[5] Huang, H., Li, J., Liu, J.. Enhanced semi-supervised local Fisher discriminant analysis for face recognition [J]. Future generations computer systems: FGCS 2012, 1(1).
[6] Zhang, T., Liu, S., Xu, C., Lu, H.. Boosted multi-class semi-supervised learning for human action recognition [J]. Pattern Recognition: The Journal of the Pattern Recognition Society 2011, 10/11(10/11).
[7] Shanwen Zhang, Ying-Ke Lei, Yan-Hua Wu. Semi-supervised locally discriminant projection for classification and recognition [J]. Knowledge-based systems 2011, 2(2).
[8] ZHU Xiaojin. Semi-supervised learning literature survey [R]. Madison:University of Wisconsin-Madison 2008.
