Journal of Jilin University(Information Science Ed ›› 2016, Vol. 34 ›› Issue (1): 153-157.

Previous Articles    

Restoration of Atmospheric Turbulence Degraded Image Based on Dictionary Learning

XU Yurui, LIU Le, WANG Ganggang, HOU Alin   

  1. College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China
  • Received:2014-12-01 Online:2016-01-25 Published:2016-05-10

Abstract:

为了消除大气湍流对图像的影响, 提高图像质量, 结合稀疏表示理论, 采用字典学习的算法处理大气湍流退化图像。将DCT 过完备字典、K-svd 全局字典和自适应字典的算法应用于图像去噪过程, 并与维纳滤波算法进行比较。结果表明, 该算法能较好地滤除大气湍流退化图像的噪声, 提高图像的峰值信噪比。仿真实验验证了稀疏表示在处理大气湍流退化图像的可行性, 对比传统算法具有更好的去噪性能。

Key words: 大气湍流, 图像复原, DCT 过完备字典, K-svd 字典, 自适应字典

CLC Number: 

  • TP391