版权说明 操作指南
首页 > 成果 > 详情

An improved single-image super-resolution algorithm through neighbor embedding and fusion of image patch

认领
导出
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Xiao, Weichu;Guo, Baolong
通讯作者:
Xiao, W.
作者机构:
[Xiao, Weichu] School of Communication and Electronic Engineering, Hunan City University, Yiyang 413002, Hunan, China
[Xiao, Weichu; Guo, Baolong] Institute of Intelligent Control and Image Engineering, Xidian University, Xi'an 710071, Shanxi, China
通讯机构:
School of Communication and Electronic Engineering, Hunan City University, China
语种:
英文
关键词:
Image fusion;Locally linear embedding;Neighbor embedding;Super resolution
期刊:
International Review on Computers and Software
ISSN:
1828-6003
年:
2012
卷:
7
期:
3
页码:
1308-1315
机构署名:
本校为第一且通讯机构
院系归属:
信息与电子工程学院
摘要:
Neighbor embedding algorithm has been widely used in single-image super-resolution (SR) reconstruction, which makes the assumption that neighbor patches embedded are contained in a single manifold. However, this is not true for SR because of "one-to-many" mappings between low-resolution (LR) and high-resolution (HR) patches. To overcome the problem, we believe that textures may be contained in multiple manifolds. Under this assumption, by considering that the middle-frequency information of LR images has greater correlation with high resolution image than low frequency. We propose an improved ...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com