首页 | 本学科首页   官方微博 | 高级检索  
     

各向异性扩散的图像复原
引用本文:赵楠,景刚,陈建军,周潇,秦发林,罗宇恒.各向异性扩散的图像复原[J].计算机与数字工程,2012,40(2):108-109,114.
作者姓名:赵楠  景刚  陈建军  周潇  秦发林  罗宇恒
作者单位:1. 重庆大学自动化学院 重庆400044
2. 重庆通信学院 重庆400035
3. 重庆大学通信工程学院 重庆400044
摘    要:根据图像复原的性质和非线性约束的原理,提出了各向异性扩散的图像复原新算法。主要思路是根据图像的纹理和边缘结构中梯度特性,采用各向异性的自适应扩散,通过最小化能量方案来极小化代价函数,同时通过定点交替迭代策略将非线性方程进行线性化处理。实验结果表明文中方法能对模糊图像的进行有效复原,提高图像的质量。

关 键 词:图像复原  全变分  各向异性  扩散

Image Restoration Based on Anisotropic Diffusions
ZHAO Nan , JING Gang , CHEN Jianjun , ZHOU Xiao , QIN Faling , LUO Yuheng.Image Restoration Based on Anisotropic Diffusions[J].Computer and Digital Engineering,2012,40(2):108-109,114.
Authors:ZHAO Nan  JING Gang  CHEN Jianjun  ZHOU Xiao  QIN Faling  LUO Yuheng
Affiliation:1.College of Automation,Chongqing University,Chongqing 400044)(2.Chongqing College of Communication,Chongqing 400035)(3.College of Communications Engineering,Chongqing University,Chongqing 400044)
Abstract:A blind restoration algorithm of diffusion based on anisotropic and nonlinear regularizations is proposed for restoring degraded images,in which the anisotropic and adaptive regularizations are adopted according to the character of image curvature and gradient.The nonlinear and spatial anisotropic regularization functions are suggested to smooth adaptively in the process of recovering the object image.Finally,the cost functions are minimized by alternate minimization scheme.The nonlinear equations are linear by fixed-point iteration scheme.Experiment results show that the proposed algorithm can restore image and can improve image quality effectively.
Keywords:image restoration  total variation  anisotropic  diffusion
本文献已被 CNKI 维普 万方数据 等数据库收录!
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