首页 | 官方网站   微博 | 高级检索  
     

Novel Spatially Adaptive Image Denoising Algorithm Based on Covariance Estimation in Wavelet Domain
作者姓名:谢志宏  沈庭芝  王海
作者单位:DepartmentofElectronicEngineering,SchoolofInformationScienceandTechnology,BeijingInstituteofTechnology,Beijing100081,China
基金项目:theMinisterialLevelAdvancedResearchFoundation( 2 0 0 2 0 960 0 0 1)
摘    要:A new method for image denoising is proposed. By analyzing image‘s statistical properties in wavelet domain, it is shown that the natural image has a strong and spatial variable covariance structure relationship in local space of sub-band. A non-direct estimation method is suggested to make an adaptive estimate of spatial variable covariance by estimating the correlation coefficient and variance of subband image separately. It can be used to estimate adaptive filtering of subband image. The experiment shows that this method can improve the image‘s SNR, and has strong ability to preserve edges.

关 键 词:空间自适应算法  图象处理  协方差估计  小波去噪  通信
收稿时间:2003/6/17 0:00:00

Novel Spatially Adaptive Image Denoising Algorithm Based on Covariance Estimation in Wavelet Domain
XIE Zhi-hong,SHEN Ting-zhi and WANG Hai.Novel Spatially Adaptive Image Denoising Algorithm Based on Covariance Estimation in Wavelet Domain[J].Journal of Beijing Institute of Technology,2003,12(4):390-394.
Authors:XIE Zhi-hong  SHEN Ting-zhi and WANG Hai
Affiliation:Department of Electronic Engineering, School of Information Science and Technology, Beijing Institute of Technology, Beijing 100081, China
Abstract:A new method for image denoising is proposed. By analyzing image's statistical properties in wavelet domain, it is shown that the natural image has a strong and spatial variable covariance structure relationship in local space of sub-band. A non-direct estimation method is suggested to make an adaptive estimate of spatial variable covariance by estimating the correlation coefficient and variance of subband image separately. It can be used to estimate adaptive filtering of subband image. The experiment shows that this method can improve the image's SNR, and has strong ability to preserve edges.
Keywords:image processing  denoising  wavelet  covariance estimation
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《北京理工大学学报(英文版)》浏览原始摘要信息
点击此处可从《北京理工大学学报(英文版)》下载全文
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-23

京公网安备 11010802026262号