基于学习的超分辨率技术  

Learning-based Super-resolution Technique

作　　者：郑丽贤[1] 何小海[1] 吴炜[1] 杨晓敏[1] 陈默[1] 

机构地区：[1]四川大学电子信息学院图像信息研究所,成都610064

出　　处：《计算机工程》2008年第5期193-195,共3页Computer Engineering

基　　金：国家自然科学基金资助项目(60372079)

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。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.

关 键 词：超分辨率 马尔可夫随机场 图像金字塔 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]