基于改进K-SVD字典学习的超分辨率图像重构

Image Super-Resolution Reconstruction Based on Improved K-SVD Dictionary-Learning

针对已有算法中字典训练的时间消耗巨大的问题,提出了一种改进的基于字典学习的超分辨率图像重构算法.本文将K-SVD字典算法和高低分辨率联合生成的思想结合起来,形成新的字典训练方法,并将由该算法生成的高低分辨率字典应用于基于稀疏表示的超分辨率重构.重构仿真实验证明算法不仅有效降低了字典训练所消耗的时间,而且能够改善重构高分辨图像的质量.

An improved super-resolution image reconstruction algorithm based on dictionary-learning is studied in order to solve the problem that the dictionary training process is time-consuming in the existing algorithms.The K-SVD dictionary algorithm is combined with the idea that the high and low resolution dictionaries can be co-generated.Then the high and low resolution dictionaries generated are used to the super-resolution reconstruction algorithm via sparse representation.Experiment results show that the algorithm can not only reduce the time of the dictionary training effectively,and also improve the quality of the reconstruction of high-resolution images.