基于QR分解的正则化邻域保持嵌入算法

doi:10.11772/j.issn.1001-9081.2016.06.1624

计算机应用 ›› 2016, Vol. 36 ›› Issue (6): 1624-1629.DOI: 10.11772/j.issn.1001-9081.2016.06.1624

基于QR分解的正则化邻域保持嵌入算法

翟冬灵¹, 王正群¹, 徐春林²

1. 扬州大学信息工程学院, 江苏扬州 225127;
2. 北方激光科技集团有限公司, 江苏扬州 225009

收稿日期:2015-11-23 修回日期:2015-12-28 出版日期:2016-06-10 发布日期:2016-06-08
通讯作者: 王正群
作者简介:翟冬灵(1991-),男,江苏启东人,硕士研究生,主要研究方向:模式识别;王正群(1965-),男,江苏如东人,教授,博士,主要研究方向:模式识别、机器学习;徐春林(1969-),男,江苏兴化人,研究员级高级工程师,博士,主要研究方向:信号处理。
基金资助:
国家自然科学基金资助项目(61402395)。

Regularized neighborhood preserving embedding algorithm based on QR decomposition

ZHAI Dongling¹, WANG Zhengqun¹, XU Chunlin²

1. College of Information Engineering, Yangzhou University, Yangzhou Jiangsu 225127, China;
2. North Laser Technology Group Company Limited, Yangzhou Jiangsu 225009, China

Received:2015-11-23 Revised:2015-12-28 Online:2016-06-10 Published:2016-06-08
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61402395).

摘要/Abstract

摘要： 针对训练样本不足时,对数据的低维子空间估计可能会产生严重偏差的问题,提出了一种基于QR分解的正则化邻域保持嵌入算法。首先,该算法定义一个局部拉普拉斯矩阵保留原始数据的局部结构;其次,将类内散度矩阵的特征谱空间划分成三个子空间,通过倒数谱模型定义的权值函数获得新的特征向量空间,进而对高维数据进行预处理;最后,定义一个邻域保持邻接矩阵,利用QR分解获得的投影矩阵和最近邻分类器进行人脸分类。与正则化广义局部保持投影(RGDLPP)算法相比,所提算法在ORL、Yale、FERET和PIE库上识别率分别提高了2个百分点、1.5个百分点、1.5个百分点和2个百分点。实验结果表明,所提算法易于实现,在小样本(SSS)下有较高的识别率。

关键词: 图嵌入, 正则化, 局部拉普拉斯矩阵, 邻域保持嵌入, QR分解

Abstract: The estimation of the low-dimensional subspace data may have serious deviation under lacking of the training samples. In order to solve the problem, a novel regularized neighborhood preserving embedding algorithm based on QR decomposition was proposed. Firstly, a local Laplace matrix was defined to preserve local structure of the original data. Secondly, the eigen spectrum space of within-class scatter matrix was divided into three subspaces, the new eigenvector space was obtained by inverse spectrum model defined weight function and then the preprocess of the high-dimensional data was achieved. Finally, a neighborhood preserving adjacency matrix was defined, the projection matrix obtained by QR decomposition and the nearest neighbor classifier were selected for face recognition. Compared with the Regularized Generalized Discriminant Locality Preserving Projection (RGDLPP) algorithm, the recognition accuracy rate of the proposed method was respectively increased by 2 percentage points, 1.5 percentage points, 1.5 percentage points and 2 percentage points on ORL, Yale, FERET and PIE database. The experimental results show that the proposed algorithm is easy to implement and has high recognition rate relatively under Small Sample Size (SSS).

Key words: graph embedding, regularization, local Laplace matrix, neighborhood preserving embedding, QR decomposition

中图分类号:

TP391.4

翟冬灵, 王正群, 徐春林. 基于QR分解的正则化邻域保持嵌入算法[J]. 计算机应用, 2016, 36(6): 1624-1629.

ZHAI Dongling, WANG Zhengqun, XU Chunlin. Regularized neighborhood preserving embedding algorithm based on QR decomposition[J]. Journal of Computer Applications, 2016, 36(6): 1624-1629.

参考文献

[1] YAN S C, XU D, ZHANG B Y, et al. Graph embedding and extensions: a general framework for dimensionality reduction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(1): 40-51.
[2] FUKUNNAGA K. Introduction to Statistical Pattern Recognition[M]. 2nd ed. San Diego: Academic Press, 1990: 210-218.
[3] REUNANEN J. Overfitting in making comparisons between variable selection methods[J]. Journal of Machine Learning Research, 2003, 3(6): 1371-1382.
[4] TURK M, PENTALND A. Eigenfaces for recognition[J]. Cognitive Neuroscience, 1991, 3(1): 71-86.
[5] BELHUMEUR P N, HESPANHA J P, KRIEGMAN D J. Eigenfaces vs. Fisherfaces: recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 711-720.
[6] ROWEIS S T, SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290(5500): 2323-2326.
[7] TENENBAUM J B, DE SILVA V, LANGFORD J C. A global geometric framework for nonlinear dimensionality reduction[J]. Science, 2000, 290(5500): 2319-2323.
[8] BELKIN M, NIYOGI P. Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural Computation, 2003, 15(6): 1373-1396.
[9] HE X F, YAN S C, HU Y X, et al. Face recognition using Laplacianfaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-340.
[10] HE X, CAI D, YAN S, et al. Neighborhood preserving embedding[C]//Proceedings of the 10th IEEE International Conference on Computer Vision. Washington, DC: IEEE Computer Society, 2005: 1208-1213.
[11] YANG J, ZHANG D, YANG J, et al. Globally maximizing, locally minimizing: unsupervised discriminant projection with applications to face and palm biometrics[J]. IEEE Transactions Pattern Analysis and Machine Intelligence, 2007, 29(4): 650-664.
[12] YU W, TENG X, LIU C. Face recognition using discriminant locality preserving projections[J]. Image Vision Computation, 2006, 24(3): 239-248.
[13] ZHANG W, XUE X,LU H, et al. Discriminant neighborhood embedding for classification[J]. Pattern Recognition, 2006, 39(11): 2240-2243.
[14] 张志伟,杨帆,夏克文,等.一种有监督的LPP算法及其在人脸识别中的应用[J].电子与信息学报,2008,3(30):539-641. (ZHANG Z W, YANG F, XIA K W, et al. A supervised LPP algorithm and its application to face recognition[J]. Journal of Electronics & Information Technology, 2008, 3(30): 539-641.)
[15] 王晓明,王士同.广义的监督局部保留投影算法[J]. 电子与信息学报,2009,31(8):1840-1845. (WANG X M, WANG S T. Generalized supervised locality preserving projection[J]. Journal of Electronics & Information Technology, 2009, 31(8): 1840-1845.)
[16] 庞彦伟,俞能海,沈道义,等.基于核邻域保持投影的人脸识别[J].电子学报,2006,34(8):1542-1544. (PANG Y W, YU N H, SHEN D Y, et al. Kernel neighborhood preserving projections for face recognition[J]. Acta Electronica Sinica, 2006, 34(8): 1542-1544.)
[17] 张大尉,朱善安.基于核邻域保持判别嵌入的人脸识别[J].浙江大学学报(工学版),2011,45(10):1842-1847. (ZHANG D W, ZHU S A. Face recognition based on kernel neighborhood preserving discriminant embedding[J]. Journal of Zhejiang University (Engineering Science), 2011, 45(10): 1842-1847.)
[18] JIANG X, BAPPADIYA M, KOT A. Eigenfeature regularization and extraction in face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(3): 383-394.
[19] PANG Y H, TEOH A B J, ABAS F S. Regularized locality preserving discriminant embedding for face recognition[J]. Neurocomputing, 2012, 77(1): 156-166.
[20] PANG Y H, TEOH A B J, HIEW F S. Locality regularization embedding for face verification[J]. Pattern Recognition, 2015, 48(8): 86-102.
[21] 辜小花,龚卫国,杨利平.正则化保局鉴别分析方法[J].模式识别与人工智能,2012,25(4):581-587.(GU X H, GONG W G, YANG L P. Regularized locality preserving discriminant analysis[J]. Pattern Recognition & Artificial Intelligence, 2012, 25(4): 581-587.)
[22] LU G F, LIN L, JIN Z. Face recognition using regularised generalised discriminant locality preserving projections[J]. IET Computer Vision, 2010, 5(2): 107-116.
[23] 穆新亮,周水生,郑颖.基于p范数的QR-KPCA人脸识别算法[J].西安理工大学学报,2015,31(1):100-105. (MU X L, ZHOU Y S. Human face recognition algorithm based on p-norm QR-KPCA[J]. Journal of Xi'an University of Technology, 2015, 31(1): 100-105.)

基于QR分解的正则化邻域保持嵌入算法

Regularized neighborhood preserving embedding algorithm based on QR decomposition

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	林筠超, 万源. 基于图结构优化的自适应多度量非监督特征选择方法[J]. 计算机应用, 2021, 41(5): 1282-1289.
[2]	贺杰安, 吴晓红, 何小海, 胡建蓉, 卿粼波. 结合图像增强和卷积神经网络的小麦不完善粒识别[J]. 计算机应用, 2021, 41(3): 911-916.
[3]	汪志远, 降爱莲, 奥斯曼·穆罕默德. 基于正则互表示的无监督特征选择方法[J]. 计算机应用, 2020, 40(7): 1896-1900.
[4]	谢琪, 徐旭, 程耕国, 陈和平. 基于新的森林优化算法的特征选择算法[J]. 计算机应用, 2020, 40(5): 1266-1271.
[5]	耿源谦, 吴传生, 刘文. 混合非凸非光滑正则化约束的模糊图像盲复原[J]. 计算机应用, 2020, 40(4): 1171-1176.
[6]	曾梦, 宁彬, 蔡之华, 谷琼. 使用深度对抗子空间聚类实现高光谱波段选择[J]. 计算机应用, 2020, 40(2): 381-385.
[7]	任珍文, 吴明娜. 基于熵自加权联合正则化最近点的图像集分类算法[J]. 计算机应用, 2019, 39(9): 2547-2551.
[8]	张斌, 罗晓清, 张战成. 基于TV-L¹结构纹理分解的图像融合质量评价算法[J]. 计算机应用, 2019, 39(9): 2701-2706.
[9]	程俊华, 曾国辉, 鲁敦科, 黄勃. 基于Dropout的改进卷积神经网络模型平均方法[J]. 计算机应用, 2019, 39(6): 1601-1606.
[10]	杨洋, 王正群, 徐春林, 严陈, 鞠玲. 基于最大间隔准则的鲁棒多流形判别局部图嵌入算法[J]. 计算机应用, 2019, 39(5): 1453-1458.
[11]	曹海燕, 冯桂, 韩雪, 方定邦, 黄鑫达. 基于深度图的3D-HEVC鲁棒视频水印算法[J]. 计算机应用, 2019, 39(3): 869-873.
[12]	陈可佳, 杨泽宇, 刘峥, 鲁浩. 基于邻域选择策略的图卷积网络模型[J]. 计算机应用, 2019, 39(12): 3415-3419.
[13]	冯明皓, 张天伦, 王林辉, 陈荣, 连少静. 改进的弹性网模型在深度神经网络中的应用[J]. 计算机应用, 2019, 39(10): 2809-2814.
[14]	李登刚, 陈香香, 李华丽, 王忠美. 基于超像素的流形正则化稀疏约束NMF混合像元分解算法[J]. 计算机应用, 2019, 39(10): 3100-3106.
[15]	杨美姣, 刘惊雷. 基于Nyström方法的偏好特征提取[J]. 计算机应用, 2018, 38(9): 2515-2522.