全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

半监督系数选择法的人脸识别

DOI: 10.3969/j.issn.1006-7043.201105090

Keywords: 半监督约束聚类, 人脸识别, 离散余弦变换, 主成分分析, 线性判别分析

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对人脸识别过程中图像数据维数过高以及需要大量类别标记的问题,提出一种半监督离散余弦变换系数选择法,用以实现数据降维并提高识别率.该算法首先将图像数据进行离散余弦变换,根据频率特征通过预掩模选取有用信息;然后进行半监督约束聚类,利用少量有标记样本的约束集,对训练图像进行聚类;根据类别搜索较高的判别系数值,获得系数选择掩模以及训练图像的投影阵.将测试图像离散余弦变换阵在此掩模上投影,计算其与训练图像投影阵距离,利用分类器进行分类.在ORL与Yale人脸数据库上的实验结果表明:所提方法的性能优于传统方法,并与主成分分析与线性判别分析进行组合,获得了90%以上的识别率.针对人脸识别过程中图像数据维数过高以及需要大量类别标记的问题,提出一种半监督离散余弦变换系数选择法,用以实现数据降维并提高识别率.该算法首先将图像数据进行离散余弦变换,根据频率特征通过预掩模选取有用信息;然后进行半监督约束聚类,利用少量有标记样本的约束集,对训练图像进行聚类;根据类别搜索较高的判别系数值,获得系数选择掩模以及训练图像的投影阵.将测试图像离散余弦变换阵在此掩模上投影,计算其与训练图像投影阵距离,利用分类器进行分类.在ORL与Yale人脸数据库上的实验结果表明:所提方法的性能优于传统方法,并与主成分分析与线性判别分析进行组合,获得了90%以上的识别率.

References

[1]  ZHAO H T, YUEN P C. Incremental linear discriminant ?analysis? for face recognition[J]. IEEE Trans Syst Man Cybern B, 2008, 38(1): 210-211.?
[2]  赵颖.基于改进的核判别分析的人脸识别算法研究[J]. 哈尔滨理工大学学报, 2010, 15(3): 19-22. ?ZHAO Ying. Research on the improved kernel discriminant analysis based on face recognition algorithm[J]. Journal of Harbin University of Science and Technology, 2010, 15(3): 19-22.?
[3]  BASU S. Semi-supervised clustering: probabilistic models, algorithms and experiments[D]. Austin: The University of Texas, 2005: 32-33.?
[4]  ZHU X J. Semi-supervised learning literature survey[R]. Madison:University of Wisconsin-Madison, 2005: 28-31.?
[5]  ZHANG S W, LEI Y K, WU Y H. Semi-supervised locally discriminant projection for classification and recognition[J]. Knowledge-Based Systems, 2011, 24(2): 341-346.?
[6]  KIRBY M, SIROVICH L. Application of the Karhunen-Loeve procedure for the characterization of human faces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12 (1): 103-108.?
[7]  牛星, 席志红, 金子正秀. 基于改进AAM的人脸特征点提取[J]. 应用科技, 2011,38(4): 35-38. ?NIU Xing, XI Zhihong, MASAHIDE Kaneko. Face feature points extraction based on refined AAM[J].Applied Science and Technology, 2011, 38(4): 35-38.?
[8]  TURK M, PENTLAND A. Eigenfaces for recognition[J]. International Journal of Cognitive Neuroscience, 1991, 3 (1): 71-86.?
[9]  苏景龙, 林天威,王科俊, 等. 视频流下的人脸检测与跟踪[J]. 应用科技, 2011, 38(3): 5-11. ?SU Jinglong, LIN Tianwei, WANG Keijun, et al. Face detection and tracking in video[J]. Applied Science and Technology, 2011, 38(3): 5-11.?
[10]  ZHUANG X S, DAI D Q. Improved discriminant analysis for high-dimensional data and its application to face recognition[J]. Pattern Recognition, 2007, 40 (5): 1570-1578.?
[11]  GAO Q X, ZHANG L, ZHANG D. Face recognition using FLDA with single training image per-person[J]. Applied Mathematics and Computation, 2008, 205 (12): 726-734.?
[12]  CAI D, HE X F, HAN J W. Semi-supervised discriminant analysis[C]// IEEE International Conference on Computer Vision. Rio de Janeiro, Brazil, 2007: 205-211.
[13]  DABBAGHCHIAN S, GHAEMMAGHAMI M, AGHAGOLZADEH A. Feature extraction using discrete cosine transform and discrimination power analysis with a face recognition technology[J]. Pattern Recognition, 2010, 43: 1431-1440.?
[14]  CHEN W, ER M J, WU S. PCA and LDA in DCT domain[J]. Pattern Recognition Letters, 2005, 26: 2474-2482.?
[15]  JIANG J, FENG G. Robustness analysis on facial image description in DCT domain[J]. Electronics Letters, 2007, 43 (24): 356-357.?
[16]  CHOI J, CHUNG Y S, KIM K H. Face recognition using energy probability in DCT domain[C]// IEEE International Conference on Multimedia and Expo. Toronto, 2006: 1549-1552.?

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133