期刊文献+

基于视图间鉴别相关性分析的手语图像识别 被引量:1

下载PDF
导出
摘要 典型相关性分析及其改进方法(Canonical Correlation Analysis, CCA)是被广泛运用于多视图特征学习的技术,但目前普遍存在的相关性分析方法并没有有效利用视图间信息,忽视了隐藏在图像内部的鉴别相关性。为了解决这一问题,提出基于视图间鉴别相关性分析(Between-View Discriminant Correlation Analysis, BVDCA)的手语图像识别算法。BVDCA在不同视图间最大化类内相关性信息,最小化类间相关性信息,从而可以达到鉴别分类的目的。进一步地,考虑到手语图像包含大量的非线性特征,提出基于核化的视图间鉴别相关性分析(Kernel Between-View Discriminant Correlation Analysis,KBVDCA),以解决线性不可分的目的。在手语图像数据集的实验结果验证了二者的有效性。
作者 蓝敏
出处 《电脑知识与技术》 2020年第15期19-21,共3页 Computer Knowledge and Technology
基金 湖南省教育厅科学研究项目(17C0195)。
  • 相关文献

参考文献2

二级参考文献23

  • 1王煜,白石,王正欧.用于Web文本分类的快速KNN算法[J].情报学报,2007,26(1):60-64. 被引量:33
  • 2Davis J W,Bobick A F.The Representation and Recognition of Action Using Temporal Templates[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,1997:928-934.
  • 3Blank M,Gorelick L,Schechtman E,et al.Actions as Spacetime Shapes[C]//Proceedings of the 10th International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2005:1395-1402.
  • 4Gorelick L,Blank M,Schechtman E,et al.Actions as Space-time Shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(12):2247-2253.
  • 5Laptev I.On Space-time Interest Points[J].Journal of Computer Vision,2005,64(2/3):107-123.
  • 6Dollar P,Vincent R,Garrison C,et al.Behavior Recognition via Sparse Spatio-temporal Features[C]//Proceedings of the2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.Washington D.C.,USA:IEEE Press,2005:65-72.
  • 7Willems G,Tuytelaars T,Van Gool L.An Efficient Dense and Scale-invariant Spatio-temporal Interest Point Detector[C]//Proceedings of the 10th European Conference on Computer Vision.Marseille,France:Springer,2008:650-663.
  • 8Wang Heng,Ullah M,Klaser A,et al.Evaluation of Local Spatio-temporal Features for Action Recognition[C]//Proceedings of British Machine Vision Conference.London,UK:Southampton,2009:1-11.
  • 9Laptev I,Marszalek M,Schmid C,et al.Learning Realistic Human Actions from Movies[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2008:1-8.
  • 10Vig E,Dorr M,Cox D.Space-variant Descriptor Sampling for Action Recognition Based on Saliency and Eye Movements[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2012:84-97.

共引文献10

同被引文献3

引证文献1

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