去除乘性噪声的二阶总广义变分模型及算法
DOI:
CSTR:
作者:
作者单位:

作者简介:

郝岩(1977-),女,博士,副教授,研究方向 为变分和偏微分方程在图像处理中的应用.

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(61301229,1)和河南科技大学博士科研基金(09001708,1)资助项目 , 许建楼 (河南科技大学 数学与统计学院,河南 洛阳 471023)


Second-order total generalized variation model and algorithm for multiplicative noise removal
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对总变分去噪模型容易导致阶梯效应的缺陷,提 出了一种新的乘性噪声去噪模型。在新模型中,二阶总广义变分(TGV)是正则项,它能自动平 衡一阶和二阶导数项,使得新模型在去除乘性噪声的同时不但能够保 持图像的边缘信息,而且还能去除阶梯效应。为了有效的计算该模型,设计了一个快速迭代算 法。在算法中,首先采用分裂方法和交替方向法将原问题变为两个相关的子问题,然后分别对 子问题利用牛顿法和原始-对偶算法。实验结果表明,与同类模型相比,本文方法无论是在视 觉效果还是定量指标,如峰值信噪比(PSNR)等都有明显地提高。

    Abstract:

    Aiming at the drawback of the total v ariational denoising model in which the staircase effect is often produced,an im proved multiplicative noise removal model based on second-order total generaliz ed variation (TGV) is proposed in this paper.In this new model,the second-order total generalized var iation is the regularization term,which can automatically balance the first order derivative and the second order deriva tive.So the proposed model makes use of the characteristics of second total generalized variation which makes the edges in the restored image preserved well and removes multiplicative noise while avoiding the staircase effect.In order to sol ve the proposed model effectively,a fast iteration algorithm is designed.In the algorithm,we first use the splitting meth od and alternating direction method to divide the primal problem into two relevant subproblems,and then the Newton meth od and primal-dual method are adopted in the respective subproblem.The comprehensive experimental results sho w that compared with the existing congeneric algorithms,the new model is more effective to filter out the existin g multiplicative noise and preserves the edges of image while avoiding the staircase effect.Therefore,the restored result s are improved in both visual effects and some quantitative indexes,such as peak signal to noise ratio.

    参考文献
    相似文献
    引证文献
引用本文

郝岩,许建楼.去除乘性噪声的二阶总广义变分模型及算法[J].光电子激光,2013,(9):1819~1824

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2012-12-17
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期:
  • 出版日期:
文章二维码