图像超分辨率的改进非局部迭代反投影法

Xiuju Liang, Z. Gan
{"title":"图像超分辨率的改进非局部迭代反投影法","authors":"Xiuju Liang, Z. Gan","doi":"10.1109/ICIG.2011.108","DOIUrl":null,"url":null,"abstract":"The non-local iterative back-projection (NLIBP) algorithm for image super-resolution proposed by Dong et al. can generate high-resolution image with sharp edges well preserved. However it may produce some unpleasant artifacts when applied to images with large shading areas, and the pixel-wise non-local post-processing is high complexity. This paper presents an improved NLIBP fast algorithm. First an edge detection is conducted on the initially interpolated image. Then the use of non-local filter in the modifying process for each initially interpolated pixel can be adaptively controlled according to the edges around, which greatly reduces the time consumption. The experimental results show that our improved algorithm reconstructs higher quality images in both the measure of PSNR and the subjective perception with lower complexity.","PeriodicalId":277974,"journal":{"name":"2011 Sixth International Conference on Image and Graphics","volume":"52 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"30","resultStr":"{\"title\":\"Improved Non-local Iterative Back-Projection Method for Image Super-Resolution\",\"authors\":\"Xiuju Liang, Z. Gan\",\"doi\":\"10.1109/ICIG.2011.108\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The non-local iterative back-projection (NLIBP) algorithm for image super-resolution proposed by Dong et al. can generate high-resolution image with sharp edges well preserved. However it may produce some unpleasant artifacts when applied to images with large shading areas, and the pixel-wise non-local post-processing is high complexity. This paper presents an improved NLIBP fast algorithm. First an edge detection is conducted on the initially interpolated image. Then the use of non-local filter in the modifying process for each initially interpolated pixel can be adaptively controlled according to the edges around, which greatly reduces the time consumption. The experimental results show that our improved algorithm reconstructs higher quality images in both the measure of PSNR and the subjective perception with lower complexity.\",\"PeriodicalId\":277974,\"journal\":{\"name\":\"2011 Sixth International Conference on Image and Graphics\",\"volume\":\"52 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-08-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"30\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2011 Sixth International Conference on Image and Graphics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICIG.2011.108\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 Sixth International Conference on Image and Graphics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIG.2011.108","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 30

摘要

Dong等人提出的非局部迭代反投影(NLIBP)图像超分辨率算法可以生成保留清晰边缘的高分辨率图像。然而,当应用于具有较大阴影区域的图像时,可能会产生一些令人不快的伪影,并且逐像素的非局部后处理非常复杂。本文提出了一种改进的NLIBP快速算法。首先对插值后的图像进行边缘检测。然后在修改过程中使用非局部滤波器,可以根据周围的边缘自适应控制每个初始插值像素,从而大大减少了时间消耗。实验结果表明,改进后的算法在PSNR和主观感知两方面都能以较低的复杂度重建出更高质量的图像。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Improved Non-local Iterative Back-Projection Method for Image Super-Resolution
The non-local iterative back-projection (NLIBP) algorithm for image super-resolution proposed by Dong et al. can generate high-resolution image with sharp edges well preserved. However it may produce some unpleasant artifacts when applied to images with large shading areas, and the pixel-wise non-local post-processing is high complexity. This paper presents an improved NLIBP fast algorithm. First an edge detection is conducted on the initially interpolated image. Then the use of non-local filter in the modifying process for each initially interpolated pixel can be adaptively controlled according to the edges around, which greatly reduces the time consumption. The experimental results show that our improved algorithm reconstructs higher quality images in both the measure of PSNR and the subjective perception with lower complexity.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信