首页 | 本学科首页   官方微博 | 高级检索  
     

多尺度域非线性能量保持的图像去噪新方法
引用本文:范燕,宋晓宁,吴小俊. 多尺度域非线性能量保持的图像去噪新方法[J]. 计算机工程与应用, 2010, 46(6): 166-168. DOI: 10.3778/j.issn.1002-8331.2010.06.048
作者姓名:范燕  宋晓宁  吴小俊
作者单位:江苏科技大学,电子信息学院,江苏,镇江,212003;南京理工大学,计算机科学与技术系,南京,210094;江南大学,信息工程学院,江苏,无锡,214122
基金项目:国家自然科学基金(No.60572034);;江苏省自然科学基金(No. BK2004058);;江苏科技大学电子信息学院青年教师科研立项资助~~
摘    要:提出了一种基于Contourlet多尺度分解域核主成分分析的图像去噪新方法。该方法首先对源图像进行Contourlet分解,在不同频段的子带图像中,利用核主成分分析方法进行能量保持,用重构图像来进行子带去噪,最后通过Contourlet逆变换得到去噪之后的图像。实验结果表明,该方法不仅有效地降低了图像噪声,且峰值信噪比也较高。

关 键 词:轮廓波变换  核主成分分析  图像去噪  多尺度分解
收稿时间:2008-08-29
修稿时间:2008-11-17 

New image denoising method based on multi-scale decomposition and nonlinear energy preserve
FAN Yan,SONG Xiao-ning,WU Xiao-jun. New image denoising method based on multi-scale decomposition and nonlinear energy preserve[J]. Computer Engineering and Applications, 2010, 46(6): 166-168. DOI: 10.3778/j.issn.1002-8331.2010.06.048
Authors:FAN Yan  SONG Xiao-ning  WU Xiao-jun
Affiliation:1.School of Electronics and Information,Jiangsu University of Science and Technology,Zhenjiang,Jiangsu 212003,China 2.Department of Computer Science and Technology,Nanjing University of Science and Technology,Nanjing 210094,China 3.School of Information Engineering,Jiangnan University,Wuxi,Jiangsu 214122,China
Abstract:A new method based on Kernel Principal Component Analysis(KPCA) in contourlet multi-scale decomposition domain is proposed in order to solve image denoising problem.Firstly,contourlet transformation is applied on source image with this method.Secondly,image denoising is executed on different frequency sub-images with reconstructed images by KPCA method.Finally,denoised image is attained with inverse contourlet transform.The experimental results on images demonstrate that the proposed method not only decreas...
Keywords:Contourlet transform  kernel principal component analysis  image denoising  multi-scale decomposition
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载免费的PDF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