Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (4): 1171-1176.DOI: 10.11772/j.issn.1001-9081.2019091647

• Virtual reality and multimedia computing • Previous Articles     Next Articles

Mixed non-convex and non-smooth regularization constraint based blind image restoration

GENG Yuanqian1, WU Chuansheng1, LIU Wen2,3   

  1. 1. School of Science, Wuhan University of Technology, Wuhan Hubei 430070, China;
    2. School of Navigation, Wuhan University of Technology, Wuhan Hubei 430063, China;
    3. Hubei Key Laboratory of Transportation of Internet of Things Technology(Wuhan University of Technology), Wuhan Hubei 430063, China
  • Received:2019-09-26 Revised:2019-11-04 Online:2020-04-10 Published:2019-11-18
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China(51609195).

混合非凸非光滑正则化约束的模糊图像盲复原

耿源谦1, 吴传生1, 刘文2,3   

  1. 1. 武汉理工大学 理学院, 武汉 430070;
    2. 武汉理工大学 航运学院, 武汉 430063;
    3. 交通物联网技术湖北省重点实验室(武汉理工大学), 武汉 430063
  • 通讯作者: 刘文
  • 作者简介:耿源谦(1995-),女,河南新乡人,硕士研究生,主要研究方向:计算机视觉、微分方程;吴传生(1957-),男,湖北天门人,教授,博士,主要研究方向:微分方程、小波分析、智能计算;刘文(1987-),男,湖北孝感人,副教授,博士,CCF会员,主要研究方向:计算机视觉、图像处理、计算航海科学。
  • 基金资助:
    国家自然科学基金资助项目(51609195)。

Abstract: In order to restore high-quality clear images,a regularization constraint based blind image restoration method was proposed. Firstly,in order to improve the accuracy of blur kernel estimation,the regularization term of L0-norm was used to perform sparsity constraint to the blur kernel according to the sparsity of blur kernel. Secondly,in order to retain the edge information of the image,the L0-norm of combining both first and second order image gradients was used to perform regularized constraint to the image gradient according to the sparsity of image gradient. Finally,since the proposed mixed regularization constraint model is essentially a non-convex and non-smooth optimization problem,the model was solved by the alternating direction method of multipliers,and the clear image was restored by using the L1-nom data fitting term and total variation method in the non-blind deconvolution stage. Experimental results show that the proposed method can restore clearer details and edge information,and has higher quality of restoration result.

Key words: blurred image, blind image restoration, regularization constraint, Alternating Direction Method of Multipliers (ADMM), total variation

摘要: 为能够复原出高质量的清晰图像,提出一种混合正则化约束的模糊图像盲复原方法。首先,根据模糊核的稀疏性,采用L0范数的正则项对模糊核进行稀疏约束,以提高模糊核估计的准确性;然后,根据图像梯度的稀疏性,采用混合一阶和二阶图像梯度的L0范数对图像梯度进行正则化约束,以保留图像边缘信息;最后,由于所提出的混合正则化约束模型本质上是非凸非光滑优化问题,通过交替方向乘子法对模型进行求解,并在非盲反卷积阶段采用L1范数数据拟合项和全变分的方法复原清晰图像。实验结果表明,所提方法能够复原出更加清晰的细节和边缘信息,复原结果的质量更高。

关键词: 模糊图像, 图像盲复原, 正则化约束, 交替方向乘子法, 全变分

CLC Number: