首页 | 本学科首页   官方微博 | 高级检索  
     

基于学习的超分辨率技术
引用本文:郑丽贤,何小海,吴炜,杨晓敏,陈默. 基于学习的超分辨率技术[J]. 计算机工程, 2008, 34(5): 193-195
作者姓名:郑丽贤  何小海  吴炜  杨晓敏  陈默
作者单位:四川大学电子信息学院图像信息研究所,成都,610064
摘    要:基于学习的超分辨率算法使用一个图像训练集来产生一个学习模型,运用该模型为输入的低分辨率图像创建更多的高频信息,获得比基于重建算法更好的结果。该文介绍了基于学习的超分辨率技术的相关工作、理论基础和主要算法,提出基于学习的超分辨率算法中仍需解决的关键问题,展望其在未来的研究发展方向。

关 键 词:超分辨率  马尔可夫随机场  图像金字塔
文章编号:1000-3428(2008)05-0193-03
收稿时间:2007-03-30
修稿时间:2007-03-30

Learning-based Super-resolution Technique
ZHENG Li-xian,HE Xiao-hai,WU Wei,YANG Xiao-min,CHEN Mo. Learning-based Super-resolution Technique[J]. Computer Engineering, 2008, 34(5): 193-195
Authors:ZHENG Li-xian  HE Xiao-hai  WU Wei  YANG Xiao-min  CHEN Mo
Affiliation:(Image Information Institute, College of Electronics and Information Engineering, Sichuan University, Chengdu 610064)
Abstract:Learuing-based super-resolution technique predicts the high-resolution images from the input low-resolution ones, through learning from a training set which consists of a large number of other high-resolution images. And the results are better than the reconstruction based super-resolution algorithms. The related work, theory and algorithms of learning-based super-resolution are illustrated. The crucial problems which need to be resolved in further work are proposed. Directions of future research are pointed.
Keywords:super-resolution   Markov random field   image pyramid
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程》浏览原始摘要信息
点击此处可从《计算机工程》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号