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...

基于关联子区域映射的多姿态人脸识别

DOI: 10.11834/jig.20070730

Keywords: 多姿态人脸识别,关联子区域映射,2维耦合成分分析,姿态补偿

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对人脸识别中的姿态变化问题,提出了子区域关联映射的方法识别多姿态的人脸图像。人脸被分割为若干子区域,姿态变化对图像的影响被分解为关联子区域的形状映射与纹理映射。提出了2维耦合成分分析的方法构造关联子区域的映射关系。2维耦合成分分析采用2维矩阵方式直接表达人脸图像,在此基础上获取不同观测空间上的低维耦合空间,根据局部几何关系不变性的原理学习耦合空间上投影特征矩阵之间的非线性映射。在应用贝叶斯框架评估子区域可分性的基础上,综合全体子区域的信息给出最终的判别结果。比较实验结果表明,关联子区域映射方法能有效补偿姿态变化带来的影响;对应的多姿态识别方法判别率高,对姿态变化敏感度低。

References

[1]  Liu X,Chen T.Pose-robust face recognition using geometry assisted probabilistic modeling[A].In:IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C],San Diego,CA,USA,2005:502~509.
[2]  Okada K,Malsburg C.Pose-invariant face recognition with parametric linear subspaces[A].In; The 5th International Conference on Automatic Face and Gesture Recognition[C],Washington DC,USA,2002:64~69.
[3]  Torre F,Black M J.Dynamic coupled component analysis[A].In:IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2001[C],Kauai Marriott,Hawaii,2001:643~650.
[4]  Yang J,Zhang D,Frangi A F,et al.Two-dimensional PCA:a new approach to appearance-based face representation and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(1):131~137.
[5]  Raytchev B,Yoda I,Sakaue K.Head pose estimation by nonlinear manifold learning[A].In; The 17th International Conference on Pattern RecognitionfC],Cambridge,UK,2004,4:462~466.
[6]  Courier N.Head Pose Image Database[EB/OL].http://www-prima.inrialpes.fr/Pointing04/data-face.html,2005-9-5.
[7]  Blanz V,Vetter T.Face recognition based on fitting a 3 Dmorphable model[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(9):1063~1074.
[8]  Lee H,Kim D.Pose invariant face recognition using linear pose transformation in feature space[A].In:ECCV 2004 Workshop on Computer Vision in Human-Computer Interaction[C],Prague,Czech Republic,2004:211~220.
[9]  Lin D,Tang X.Coupled Space learning for image style transformation[A].In; The 10th IEEE International Conference on Computer Vision[C],Beijing,China,2005,2:1699~1706.
[10]  Roweis S T,Saul L K,Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,290(5500):2323~2326.
[11]  Hancock P.Psychological Image Collection at Stirling[EB/OL].http://pics.psych,stir.ac.uk/,2005-8-26.
[12]  Kanade T,Yamada A.Multi-subregion based probabilistic approach toward pose-invariant face recognition[A].In:IEEE International Symposium on Computational Intelligence in Robotics Automation[C],Kobe,Japan,2003,2:954~959.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133