首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于自适应参数的全变分综合图像去噪模型
引用本文:范立南,黄鹤,田丹,林之娜.基于自适应参数的全变分综合图像去噪模型[J].沈阳大学学报,2013(5):383-388.
作者姓名:范立南  黄鹤  田丹  林之娜
作者单位:[1]沈阳大学信息工程学院,辽宁沈阳110044 [2]沈阳化工大学科亚学院,辽宁沈阳110167
基金项目:辽宁省自然科学基金资助项目(20102154);辽宁省教育厅科研项目计划资助项目(L2010376).
摘    要:分析了ROF去噪模型和LLT去噪模型的优缺点,提出了一种基于自适应参数的全变分综合图像去噪模型.先利用高斯滤波对噪声图像进行预处理,以减少噪声在后续处理时被当成假边缘的可能性,再根据图像中每一像素点的梯度信息,自适应地选取模型中决定平滑强弱的参数,使模型能在接近图像边缘处平滑较弱,在远离边缘处平滑较强.实验表明,本模型在去噪的同时能有效地保留图像的纹理信息,并对降噪性能指标有较好的提高.

关 键 词:图像去噪  ROF模型  LLT模型  综合模型  自适应参数

Comprehensive Total Variation Denoising Model Based on Adaptive Parameters
Fan Linan,Huang He,Tian Dan,Lin Zhina.Comprehensive Total Variation Denoising Model Based on Adaptive Parameters[J].Journal of Shenyang University,2013(5):383-388.
Authors:Fan Linan  Huang He  Tian Dan  Lin Zhina
Institution:1. School of Information Engineering, Shenyang University, Shenyang 110044, China; 2. Ke Ya College, Shenyang University of Chemical Technology, Shenyang 110167, China)
Abstract:An adaptive parameter of image denoising comprehensive model based on total variation is proposed by analyzing the two important denoising models: ROF model and LLT model. Firstly, the convolution of the Gaussian filter and the noisy image can remove a small portion of the noise so it is less likely to be detected as an edge; then the most appropriate denoising scheme is selected adaptively based on the gradient information of each pixel. Numerical experiments show that the proposed method can remove the noise while preserving significant image texture information, and improve the noise reduction performance indicator.
Keywords:image denoising  ROF model  LLT model  comprehensive model  adaptive parameter
本文献已被 CNKI 维普 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