期刊文献+

潜在空间的多视角低分辨人脸识别算法

Multiview low resolution face recognition in latent space
下载PDF
导出
摘要 提出了一种基于回归的人脸识别算法,采用偏最小二乘法为正面高分辨率特征和侧面低分辨率特征建立潜在空间,在潜在空间中利用岭回归获得正面高分辨率潜在特征和侧面低分辨率潜在特征间的线性关系。在标准图库上的实验证明了提出算法的有效性。 A regression based method is proposed for face recognition. The linear regression models from the specikfic non-frontal low resolutionimage to frontal high resolution features are learnt by ridge regression in latent space built by partial least squares. Experiments on benchmark database show the superiority of the proposed method.
作者 曾啸 黄华
出处 《中国科技论文》 CAS 北大核心 2015年第8期928-932,947,共6页 China Sciencepaper
基金 高等学校博士学科点专项科研基金资助项目(20110201110065 20110201110012)
关键词 模式识别 非正面人脸识别 低分辨率 偏最小二乘法 pattern recognition non-frontal face recognition low resolution partial least squares
  • 相关文献

参考文献15

  • 1Li Annan, Shan Shiguang, Chen Xilin, et al. Maximi zing intra-individual correlations for face recognition across pose differences [C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2009: 605-611.
  • 2Sharma A, Dubey A, Jagannatha A N, et al. Pose in variant face recognition based on hybrid global linear re- gression [J]. Neural Computing and Applications, 2010, 19(8).. 1227-1235.
  • 3Chai Xiujuan, Shan Shiguang, Chen Xilin, et al. Local ly linear regression for pose-invariant face recognition [J]. IEEE Transactions on Image Process, 2007, 16 (7) : 1716-1725.
  • 4Jia Kui, Gong Shaogang. Multi-modal tensor face for simultaneous superesolution and recognition [ C ]// Tenth IEEE International Conference on Computer Vi- sion. Beijing, China, 2005: 1683-1690.
  • 5张琳彦,吴宁,齐春.基于线性映射的灰度级超分辨率人脸识别方法[J].中国科技论文在线,2011,6(7):482-488. 被引量:3
  • 6黄昉,张宝昌,刘金琨.PCA在人脸识别中的改进算法[J].中国科技论文在线,2011,6(1):54-58. 被引量:9
  • 7Deng Weihong, Hu Jiani, Lu Jiwen, et al. Transform- invariant PCA: a unified approach to fully automatic face alignment, representation, and recognition [J]. IEEN Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(6): 1275-1284.
  • 8Cho H, Roberts R, Jung B, et al. An efficient hybrid face recognition algorithm using PCA and GABOR wavelets [J]. International Journal of Advanced Robotic Systems, 2014, 11: 54.
  • 9Wu Wei, Liu Zheng, He Xiaohai. Learning-based super resolution using kernel partial least squares [J]. Image and Vision Computing, 2011, 29(6): 394-406.
  • 10Ogawa Y, Hori T, Takiguchi T, et al. Super-resolu- tion using GMM and PLS regression [C]// 14th IEEE International Symposium on Multimedia. New York: IEEE, 2012: 298-301.

二级参考文献23

  • 1Peter H. Sch?nemann.A generalized solution of the orthogonal procrustes problem[J]. Psychometrika . 1966 (1)
  • 2Smith L.A tutorial on principal component analysis. http://users.e cs.soton.ac.uk/hbr03r/pa037042.pdf . 2002
  • 3Huang Hua,Wu Ning,Fan Xin,et al.Face image super resolution bylinear transformation. 17th IEEE International Conference onImage Processing(ICIP .2010) . 2010
  • 4Wang C,Mahadevan S.Manifold alignment using procrustes analysis. Proceedings of International Conference on Machine Learning . 2008
  • 5The ORL Face Database.[Z/OL]. http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html . 2011
  • 6Han Hu,Shan Shiguang,Chen Xilin,et al.Gray-scale super-resolutionfor face recognition from low gray-scale resolution face images. IEEE International Conference on Image Processing . 2010
  • 7Huang Hua,He Huiting,Fan Xin,et al.Super-resolution of human faceimage using canonical correlation analysis. Pattern Recognition . 2010
  • 8Huang Hua,He Huiting.Super-resolution method for face recognitionusing nonlinear mappings on coherent features. IEEE Transactionson Neural Networks . 2011
  • 9Wang Zhifei,Miao Zhenjiang.Feature-based super-resolution for facerecognition. IEEE International Conference on Multimedia andExpo (ICME) . 2008
  • 10Pablo H Y,Baker S,Kumar B V.Simultaneous Super-Resolution and Feature Extraction for Recognition of Low-Resolution Faces. Conference on Computer Vision and Pattern Recognition . 2008

共引文献10

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