二维多样性保持投影及人脸识别

doi:10.3969/j.issn.1001-2400.2012.06.006

J4 ›› 2012, Vol. 39 ›› Issue (6): 34-41.doi: 10.3969/j.issn.1001-2400.2012.06.006

二维多样性保持投影及人脸识别

侯俊^1,2;郝秀娟¹;谢德燕¹;高全学¹

(1. 西安电子科技大学通信工程学院，陕西西安 710071；
2. 西北工业大学自动化学院，陕西西安 710069)

收稿日期:2011-11-23 出版日期:2012-12-20 发布日期:2013-01-17
通讯作者: 侯俊
作者简介:侯俊(1975-)，男，副教授，博士，E-mail: xd_hj_pr@163.com．
基金资助:
国家自然科学基金资助项目(60802075, 61271296);ISN国家重点实验室自主资助项目;中央高校基本科研业务费专项资金资助项目;高等学校创新引智计划资助项目(B08038);西北工业大学科技创新基金资助项目(2008KJ02025);陕西省自然科学基础研究计划资助项目(2010JQ8032, 2012JM8002)

Face recognition using two-dimensional diversity preserving projection

HOU Jun^1,2;HAO Xiujuan¹1;XIE Deyan¹;GAO Quanxue¹

(1. School of Telecommunication Engineering, Xidian Univ., Xi'an 710071， China;
2. School of Automation, Northwestern Polytechnical Univ., Xi'an 710069， China)

Received:2011-11-23 Online:2012-12-20 Published:2013-01-17
Contact: HOU Jun

摘要/Abstract

摘要：

流形学习有效地保持了数据的局部几何结构，已成为模式识别、机器学习等领域的研究热点．但是它忽略甚至破坏了对模式分析很重要的局部多样性信息，导致局部几何结构描述不够稳定，且性能不是很好．针对此问题，提出了基于图论的多样性保持投影．该方法利用邻接图刻画局部数据之间的变化关系，并给出度量数据多样性大小的差异离散度，然后通过最大化差异离散度提取投影方向．此外，该方法直接从图像矩阵估计差异离散度矩阵，有效地避免了小样本问题．在Yale，UMIST和AR数据库上的实验结果证实了该算法的有效性．

关键词: 差异邻接图, 流形学习, 特征提取, 人脸识别

Abstract:

Previous work has demonstrated that manifold learning can effectively preserve the local geometry among nearby data, and has become an active topic in pattern recognition and machine learning. However, it ignores or even impairs the local diversity of data, which will impair the recognition accuracy and lead to unstable local geometrical structure representation. In this paper, a novel approach, namely two-dimensional diversity preserving projection (2DDPP), is proposed for dimensionality reduction. 2DDPP constructs an adjacency graph to model the variation of data and measures the variation among nearby data by the diversity scatter, on the basis of which a concise criterion is raised by maximizing the diversity scatter. Moreover, 2DDPP directly calculates the diversity scatter matrix from the image matrix, which effectively avoids the small sample size problem. Experiments on Yale, UMIST, and AR databases show the effecitveness of the proposed method.

Key words: diversity adjacency graph, manifold learning, feature extraction, face recognition

侯俊;郝秀娟;谢德燕;高全学. 二维多样性保持投影及人脸识别[J]. J4, 2012, 39(6): 34-41.

HOU Jun;HAO Xiujuan;XIE Deyan;GAO Quanxue. Face recognition using two-dimensional diversity preserving projection[J]. J4, 2012, 39(6): 34-41.

参考文献

［1］ Jiang X D. Linear Subspace-based Dimensionality Reduction ［J］. IEEE Signal Proc Magazine, 2011, 28(2): 16-26.
［2］ Yan S C, Xu D, Zhang B Y, et al. Graph Embedding and Extensions: a General Framework for Dimensionality Reduction ［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(1): 40-51.
［3］ Fan Z Z, Xu Y, Zhang D. Local Linear Discriminant Analysis Framework Using Sample Neighbors［J］. IEEE Trans on Neural Networks, 2011, 22(7): 1119-1132.
［4］ Turk M, Pentland A P. Face Recognition Using Eigenfaces ［C］//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Maui: IEEE Comput Sco Press, 1991: 586-591.
［5］ Yang J, Zhang D, Frangi A F, et al. Two-dimensional PCA: a New Approach to Appearance-based Face Representation and Recognition ［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004, 26(1): 131-137.
［6］高全学, 梁彦, 潘泉, 等. 基于描述特征的人脸识别研究［J］. 自动化学报, 2006, 32(3): 386-392.
Gao Quanxue, Liang Yan, Pan Quan, et al. Face Recognition Based on Expressive Features ［J］. ACTA Automatica Sinica, 2006, 32(3): 386-392.
［7］ Jiang X D. Asymmetric Principal Component and Discriminant Analyses for Pattern Classification ［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 2009, 31(5): 931-937.
［8］ Luo D J, Ding C, Nie F P, et al. Cauchy Graph Embedding［C］//Proc of the 28th International Conference on Machine Learning. Bellevue: Association for Computing Machinery, 2011: 553-560.
［9］ Tenenbaum J B, de Silva V, Langford J C. A Global Geometric Framework for Nonlinear Dimensionality Reduction ［J］. Science, 2000, 290: 2319-2323.
［10］ Ham J, Lee D D, Mika S, et al. A Kernel View of the Dimensionality Reduction of Manifolds ［C］//Proc of Twenty-First International Conference on Machine Learning. Banff: Association for Computing Machinery, 2004: 369-376.
［11］ Scholkopf B, Smola A, Müller K R. Nonlinear Component Analysis as a Kernel Eigenvalue Problem ［J］. Neural Computation, 1998, 15(5): 1299-1319.
［12］ He X F, Yan S C, Hu Y X, et al. Face Recognition Using Laplacianfaces ［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-340.
［13］ Xu Y, Song F X, Feng G, et al. A Novel Preserving Projection for Use with Face Recognition ［J］. Expert Systems with applications, 2010, 37: 6718-6721.
［14］ Gao Q X, Zhang H J, Liu J J. Two-dimensional Margin, Similarity and Variation Embedding ［J］. Neurocomputing, 2012, 86: 179-183.
［15］ Dai G, Yeung D Y. Tensor Embedding Methods ［C］//Proc of American Association for Artificial Intelligence (AAAI). Boston: American Association for Artificial Intelligence, 2006: 330-335.
［16］ Hu D W, Feng G Y, Zhou Z T. Two-dimensional Locality Preserving Projections (2DLPP) with Its Application to Palmprint Recognition ［J］. Pattern Recognition, 2007, 40 (1): 339-342.
［17］ Gao Q X, Xu H, Li Y Y, et al. Two-dimensional Supervised Local Similarity and Diversity Projection ［J］. Pattern Recognition, 2010, 43(10): 3359-3363.
［18］高全学, 谢德燕, 徐辉, 等. 融合局部结构和差异信息的监督特征提取方法［J］. 自动化学报, 2010, 36(8): 1107-1114.
Gao Quanxue, Xie Deyan, Xu Hui, et al. Supervised Feature Extraction Based on Information Fusion of Local Structure and Diversity Information ［J］. ACTA Automatica Sinica, 2010, 36(8): 1107-1114.
［19］ Liu K, Cheng Y, Yang J Y. Algebraic Feature Extraction for Image Recognition Based on an Optimal Discriminant Criterion ［J］. Pattern Recognition, 1993, 26(6): 903-911.
［20］ Yang J, Zhang D, Yang J Y, et al. Globally Maximizing, Locally Minimizing: Unsupervised Discriminant Projection with Applications to Face and Palm Biometrics ［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(4): 650-664.

[1]	刘洁怡,公茂果,詹涛,李豪,张明阳. 一种深度神经网络多站雷达系统干扰鉴别方法[J]. 西安电子科技大学学报, 2021, 48(2): 133-138.
[2]	魏梓钰,杨曦,王楠楠,杨东,高新波. 互惠双向生成对抗网络用于跨模态行人重识别[J]. 西安电子科技大学学报, 2021, 48(2): 205-212.
[3]	郭泽坤,田隆,韩宁,王鹏辉,刘宏伟,陈渤. 采用CNN-SSD的雷达HRRP小样本目标识别方法[J]. 西安电子科技大学学报, 2021, 48(2): 7-14.
[4]	韩卓茜,王锋,陈沛,李卓伦. 一种历史特征辅助的模糊数据关联算法[J]. 西安电子科技大学学报, 2021, 48(2): 92-98.
[5]	王晓华,要鹏超,马丽萍,王文杰,张蕾. 车间环境下机器人语音控制的特征提取算法[J]. 西安电子科技大学学报, 2020, 47(2): 16-22.
[6]	欧阳宁,王先傲,蔡晓东,林乐平. 结合小波与递归神经网络的低分辨率人脸识别[J]. 西安电子科技大学学报, 2019, 46(6): 95-101.
[7]	王红艳,朱利民,张潘杰,李金屏. 一种利用外轮廓配准的活塞侧面缺陷检测方法[J]. 西安电子科技大学学报, 2019, 46(5): 75-83.
[8]	郭睿,臧博,彭树铭,邢孟道. 高分辨InSAR中的城市高层建筑特征提取[J]. 西安电子科技大学学报, 2019, 46(4): 137-143.
[9]	刘道华,崔玉爽,赵岩松,宋玉婷,王景慧. 一种改进卷积神经网络的教学图像检索方法[J]. 西安电子科技大学学报, 2019, 46(3): 52-58.
[10]	杨建功,汪西莉,刘侍刚. 融合谱-空域信息的DBM高光谱图像分类方法[J]. 西安电子科技大学学报, 2019, 46(3): 109-115.
[11]	王欣远,肖嵩,李磊,焦玲玲. 融合ELM和相关滤波的鲁棒性目标跟踪算法[J]. 西安电子科技大学学报, 2019, 46(1): 57-63.
[12]	梁晓曦, 蔡晓东, 王萌, 库浩华. NRCNN与角度度量融合的人脸识别方法[J]. 西安电子科技大学学报, 2018, 45(6): 144-149.
[13]	汪星;黄小瑜;刘瑄璞;孔宪光;牛萌. 面向工业大数据的多层增量特征提取方法[J]. 西安电子科技大学学报, 2018, 45(4): 106-111.
[14]	贺王鹏;孙伟;苏博;闫允一;郭宝龙. 机械故障诊断的稀疏特征提取方法[J]. 西安电子科技大学学报, 2018, 45(2): 154-159.
[15]	张雨禾;耿国华;魏潇然;石晨晨;张顺利. 采用密度空间聚类的散乱点云特征提取方法[J]. 西安电子科技大学学报, 2017, 44(2): 114-120.

二维多样性保持投影及人脸识别

Face recognition using two-dimensional diversity preserving projection

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0