各向异性扩散的图像复原  

Image Restoration Based on Anisotropic Diffusions

作　　者：赵楠[1] 景刚[2] 陈建军[3] 周潇[3] 秦发林[3] 罗宇恒[3] 

机构地区：[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

出　　处：《计算机与数字工程》2012年第2期108-109,114,共3页Computer & Digital Engineering

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。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.

关 键 词：图像复原 全变分 各向异性 扩散 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]