Pairwise comparison and rank learning for image quality assessment
详细信息 查看全文
- 作者：Long Xua ; lxu@nao.cas.cn" class="auth_mail" title="E-mail the corresponding author ; Jia Lib ; jiali@buaa.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Weisi Linc ; WSLin@ntu.edu.sg" class="auth_mail" title="E-mail the corresponding author ; Yun Zhangd ; yun.zhang@siat.ac.cn" class="auth_mail" title="E-mail the corresponding author ; Yongbing Zhange ; zhang.yongbing@sz.tsinghua.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Yihua Yana ; yyh@nao.cas.cn" class="auth_mail" title="E-mail the corresponding author
- 关键词：Image quality assessment ; Machine learning ; Rank learning ; Pairwise comparison
- 刊名：Displays
- 出版年：2016
- 出版时间：September 2016
- 年：2016
- 卷：44
- 期：Complete
- 页码：21-26
- 全文大小：406 K
文摘
- •
Pairwise comparison (PC), rather than conventional numerical rating of image quality, is explored for IQA.
- •
A new optimization objective for optimizing image quality ranks is established.
- •
Image quality ratings are used as weights in rank model additionally, making it rating-sensitive.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |