Pre-classified learning based image super-resolution algorithm - 文章详情页

作者：

Cao, Y. (Cao, Y..) | Li, X. (Li, X..) | Wang, S. (Wang, S..) | Shen, L. (Shen, L..)

收录：

Scopus PKU CSCD

摘要：

Learning-based　image　super-resolution　is　one　of　the　most　promising　approaches　to　solve　the　image　super-resolution　problem.　A　novel　pre-classified　learning　based　image　super-resolution　algorithm　is　proposed　to　reduce　the　complexity　of　full　searching　and　to　avoid　mismatching.　A　texture-based　pre-classified　process　is　used　to　select　a　subset　of　samples.　Then,　the　best-matching　samples　are　searched　among　the　selected　subsets.　In　the　proposed　algorithm,　the　complexity　of　the　searching　process　is　effectively　reduced　by　the　texture-based　pre-classified　process.　Furthermore,　using　the　texture　features,　the　mismatching　probability　is　reduced.　Experimental　results　show　that　both　the　visual　quality　and　the　run-time　are　improved.

关键词：

Learning; Super-resolution; Texture features; Training set

作者机构：

[ 1 ] [Cao, Y.]Signal and Information Processing Lab, Beijing University of Technology, Beijing 100124, China
[ 2 ] [Li, X.]Signal and Information Processing Lab, Beijing University of Technology, Beijing 100124, China
[ 3 ] [Wang, S.]Signal and Information Processing Lab, Beijing University of Technology, Beijing 100124, China
[ 4 ] [Shen, L.]Signal and Information Processing Lab, Beijing University of Technology, Beijing 100124, China

通讯作者信息：

[Cao, Y.]Signal and Information Processing Lab, Beijing University of Technology, Beijing 100124, China

电子邮件地址：

xiaorancy@emails.bjut.edu.cn

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至