期刊文献+

基于非线性流形学习的人脸面部运动估计 被引量:5

Human Face Analysis with Nonlinear Manifold Learning
下载PDF
导出
摘要 由于人脸面部运动变化分布在一个低维非线性流形中,基于线性假设的主动外观模型采用主成分分析算法描述人脸形状的变化必然带来额外的估计误差。为降低或消除这一误差,该文提出一种改进的局部线性嵌入算法构建人脸形状-纹理空间,并将其应用于主动外观模型中。实验结果表明,不仅对于面部形变不大的人脸形状,局部线性嵌入-主动外观模型拥有更低的估计残差;而且对于一些变化较大的人脸形状,在主成分分析-主动外观模型跟踪失败的情况下,局部线性嵌入-主动外观模型依然可以取得很好的特征估计结果,弥补了主成分分析-主动外观模型的不足。 Since human face movements distribute on a nonlinear manifold, there are inherent alignment residuals brought by the global linearity hypothesis in the traditional Principal Component Analysis (PCA) based Active Appearance Models (AAM). In this paper, a famous manifold learning method, Local Linear Embedding (LLE) is improved to model human face shape space for reducing the inherent alignment residuals. The experimental results show that the method, LLE-AAM, obtains lower alignment residuals to the tiny alterations of human face and still make successful alignment when PCA-AAM failed to some large alterations. According to the statistical analysis, LLE-AAM could reduce the residual to a certain extent.
出处 《电子与信息学报》 EI CSCD 北大核心 2011年第10期2531-2535,共5页 Journal of Electronics & Information Technology
基金 国家科技部中日国际科技合作项目(2010DFA11990) 国家自然科学基金(60873269)资助课题
关键词 人脸识别 主动外观模型 非线性流形学习 局部线性嵌入 Face recognition Active Appearance Models (AAM) Nonlinear manifold learning Local Linear Embedding (LLE)
  • 相关文献

参考文献13

  • 1Edwards G J, Taylor C J, and Cootes T F. Learning to identify and track faces in image sequences[C]. Third IEEE International Conference on Automatic Face and Gesture Recognition, India, Apr. 14-16, 1998: 260-265.
  • 2Xiao R, Zhao Q, Zhang D, et al.. Facial expression recognition on multiple manifolds[J]. Pattern Recognition. 2011, 44(1): 107-116.
  • 3Papandreou G and Maragos P. Adaptive and constrained algorithms for inverse compositional Active Appearance Model fitting[C]. IEEE Conference on Computer Vision and Pattern Recognition, USA, 2008: 1-8.
  • 4Tuzel O, Porikli F, and Meer P. Pedestrian detection via classification on Riemannian manifolds[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(10): 1713-1727.
  • 5Huckemann S, Hotz T, and Munk A. Intrinsic MANOVA for Rieinannian manifolds with an application to Kendall's space of planar shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 593-603.
  • 6Lee C S and Elgammal A. Tracking people on a torus[R]. Tech. Rep., Department of Computer Science, Rutgers University, 2007.
  • 7Yang M H. Face recognition using extended isomap[C]. International Conference on Image Processing, USA, 2002, (2): 117-120.
  • 8Roweis S T and Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290(5500): 2323.
  • 9叶奇明,梁根.融合主动外观模型与局部二元模式的人脸识别[J].湖北大学学报(自然科学版),2010,32(2):146-150. 被引量:1
  • 10Matthews I and Baker S. Active appearance models revisited[J]. International Journal of Computer Vision, 2004, 60(2): 135-164.

二级参考文献22

  • 1王蕴红,范伟,谭铁牛.融合全局与局部特征的子空间人脸识别算法[J].计算机学报,2005,28(10):1657-1663. 被引量:41
  • 2Zhou Yong,Li You-wen,and Xia Shi-xiong.An improved KNN text classification algorithm based on clustering.Journal of Computers,2009,4(3):230-237.
  • 3Fuknshima Tamon,Yamamori Kunihito,and Yushihara Ikuo,et al..Feature extraction of protein expression levels based on classification of functional foods with SOM.Artificial Life and Robotics,2009,13(2):543-546.
  • 4Park Cheong-hee and Lee Moonhwi.A SVM-based discretization method with application to associative classification.Expert Systems with Applications,2009,36(3):4784-4787.
  • 5Zhang Yong,Ren Yong-gong,and Zhang Zai-yue,et al..Fuzzy SVDD classifier with positive and negative samples,Journal of Computational Information Systems,2008,4(3):1055-1062.
  • 6Tenenbaum J B,Silva V,and Langford J C.A global geometric framework for nonlinear dimensionality reduction.Science,2000,290(5500):2319-2323.
  • 7Roweis S T and Saul L K.Nonlinear dimensionality reduction by locally linear embedding.Science,2000,290(5500):2323-2326.
  • 8Belkin M and Niyogl P.Laplacian eigenmaps for dimensionality reduction and data representation.Neural Computation,2003,15(6):1373-1396.
  • 9Zhang Zhen-yue and Zha Hong-yuan.Principal manifold and nonlinear dimension reduction via local tangent space alignment,SIAM Journal of Scientific Computing,2004,26(1):313-338.
  • 10Chang H and Yeung D Y.Locally linear metric adaptation with application to semi-supervised clustering and image retrieval.Pattern Recognition,2006,39(7):1253-1264.

共引文献3

同被引文献31

引证文献5

二级引证文献27

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部