Improving Image Restoration with Soft-Rounding
Mei, Xing1,3; Qi, Honggang2; Hu, Bao-Gang3; Lyu, Siwei1
2015
会议名称International Conference on Computer Vision (ICCV)
会议日期2015
会议地点Santiago, Chile
摘要
Several important classes of images such as text, barcode and pattern images have the property that pixels can only take a distinct subset of values. This knowledge can benefit
the restoration of such images, but it has not been widely considered in current restoration methods. In this work, we describe an effective and efficient approach to incorporate
the knowledge of distinct pixel values of the pristine images into the general regularized least squares restoration frame-work. We introduce a new regularizer that attains zero at the designated pixel values and becomes a quadratic penalty function in the intervals between them. When incorporated into the regularized least squares restoration framework, this regularizer leads to a simple and efficient step that re-
sembles and extends the rounding operation, which we term as soft-rounding. We apply the soft-rounding enhanced solution to the restoration of binary text/barcode images and
pattern images with multiple distinct pixel values. Experimental results show that soft-rounding enhanced restoration methods achieve significant improvement in both visual
quality and quantitative measures (PSNR and SSIM). Furthermore, we show that this regularizer can also benefit the restoration of general natural images.
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/20005
专题模式识别国家重点实验室_多媒体计算与图形学
作者单位1.Computer Science Department, University at Albany, SUNY
2.Computer Science Department, University of Chinese Academy of Sciences
3.NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China
推荐引用方式
GB/T 7714
Mei, Xing,Qi, Honggang,Hu, Bao-Gang,et al. Improving Image Restoration with Soft-Rounding[C],2015.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Improving Image Rest(2505KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Mei, Xing]的文章
[Qi, Honggang]的文章
[Hu, Bao-Gang]的文章
百度学术
百度学术中相似的文章
[Mei, Xing]的文章
[Qi, Honggang]的文章
[Hu, Bao-Gang]的文章
必应学术
必应学术中相似的文章
[Mei, Xing]的文章
[Qi, Honggang]的文章
[Hu, Bao-Gang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Improving Image Restoration with Soft-Rounding.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。