检索结果-内蒙古大学图书馆

A New Fast Bloc Matching algorithm Using Unsupervised Bayesian Classifier with bootstrap gaussian expectation maximization algorithm

引用

SN Computer Science 2023年第3期4卷 1-8页

作者： Kerfa, Djoudi Ghorbel, Faouzi CaSiCCE Research Laboratory Electrical Department National School of Polytechnic Engineering of Oran Maurice Audin (Ex-Enset) PB 1523 El M’Naouar 31000 Algeria Cristal Research Laboratory National School of Informatics Sciences Campus University Manouba 2010 Tunisia

This paper proposes a two-step block matching algorithm for motion estimation. To reduce the algorithmic complexity, the unsupervised Bayesian classifier with resampling bootstrap gaussian expectation of maximization algorithm serves to detect the static and dynamic blocks, and the bloc matching algorithm with star diamond pattern is used to search final position of dynamic blocks. A comparative study with other algorithms has shown the proposed method can achieve faster computation with good PSNR values. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Block matching algorithm bootstrap gaussian expectation maximization algorithm Motion estimation Unsupervised Bayesian classifier

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还