首页 | 本学科首页   官方微博 | 高级检索  
     

基于预测稀疏编码的快速单幅图像超分辨率重建
引用本文:沈辉,袁晓彤,刘青山.基于预测稀疏编码的快速单幅图像超分辨率重建[J].计算机应用,2015,35(6):1749-1752.
作者姓名:沈辉  袁晓彤  刘青山
作者单位:江苏省大数据分析技术重点实验室(南京信息工程大学), 南京 210044
基金项目:国家自然科学基金资助项目,江苏省自然科学基金资助项目
摘    要:针对经典的基于稀疏编码的图像超分辨率算法在重建过程中运算量大、计算效率低的缺点,提出一种基于预测稀疏编码的单幅图像超分辨率重建算法。训练阶段,该算法在传统的稀疏编码误差函数基础上叠加编码预测误差项构造目标函数,并采用交替优化过程最小化该目标函数;测试阶段,仅需将输入的低分辨图像块和预先训练得到的低分辨率字典相乘就能预测出重建系数,从而避免了求解稀疏回归问题。实验结果表明,与经典的基于稀疏编码的单幅图像超分辨率算法相比,该算法能够在显著减少重建阶段运算时间的同时几乎完全保留超分辨率视觉效果。

关 键 词:图像超分辨率    预测稀疏编码    字典学习    交替优化
收稿时间:2014-12-29
修稿时间:2015-03-22

Fast super-resolution reconstruction for single image based on predictive sparse coding
SHEN Hui,YUAN Xiaotong,LIU Qingshan.Fast super-resolution reconstruction for single image based on predictive sparse coding[J].journal of Computer Applications,2015,35(6):1749-1752.
Authors:SHEN Hui  YUAN Xiaotong  LIU Qingshan
Affiliation:Jiangsu Key Laboratory of Big Data Analysis Technology (Nanjing University of Information Science and Technology), Nanjing Jiangsu 210044, China
Abstract:The classic super-resolution algorithm via sparse coding has high computational cost during the reconstruction phase. In view of the disadvantages, a predictive sparse coding-based single image super-resolution method was proposed. In the training phase, the proposed method imposed a code prediction error term to the traditional sparse coding error function, and used an alternating minimization procedure to minimize the resultant objective function. In the testing phase, the reconstruction coefficient could be estimated by simply multiplying the low-dimensional image patch with the low-dimensional dictionary, without any need to solve sparse regression problems. The experimental results demonstrate that, compared with the classic single image super-resolution algorithm via sparse coding, the proposed method is able to significantly reduce the reconstruction time while maintaining super-resolution visual effect.
Keywords:image super-resolution  predictive sparse coding  dictionary learning  alternative optimization
本文献已被 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》下载全文
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