期刊文献+

多邻域中值滤波算法在医学图像中的应用 预览

The application of multi-neighborhood median filterin medical images
在线阅读 免费下载
分享 导出
摘要 目的:克服现有的滤波算法在噪声检测与噪声滤除上的缺陷,进一步提高去噪性能.方法:提出了多邻域中值滤波算法,对噪声检测和噪声滤除的方法分别进行改进.算法用邻域中的灰度极值进行噪声检测,对检测出来的可疑噪声,用邻域的中值作进一步的噪声检测.对噪声像素,在其邻近的9个邻域中分别求出信号像素的中值,然后用所有中值的中值作为噪声像素新的灰度.结果:基于医学图像的实验结果证明,相对于现有的算法,所提出的算法的去噪图像更加清晰,去噪结果的PSNR和SSIM值更高.结论:所提出的算法在彻底去除噪声的同时,很好地保持了图像的纹理边缘和细节,相对于现有的滤波算法,具有更好的去噪性能. Objective:To overcome the drawbacks of existing filters in noise detection and removal,and further improve the denoising performance.Methods:We propose a multi-neighborhood median filter to improve the techniques of noise detection and removal.This proposed filter first performs noise detection by the extreme intensity values of neighborhood,and then performs further noise detection by the median of neighborhood.For noisy pixel,it searches for the medians of nine neighboring neighborhood respectively,and then take the median of all medians as the new intensity of noisy pixel.Results:The experimental results with medical images,show that compared to the existing filters,the propose method obtains clearer denoised images,and achieves higher PSNR and SSIM values.Conclusion:The proposed method can preserve the edges and details of image very well,while removing the noises thoroughly;comparing to the existing filters,the proposed method shows better denoising performance.
作者 陈家益 董梦艺 战荫伟 曹会英 熊刚强 CHEN Jiayi;DONG Mengyi;ZHAN Yinwei;CAO Huiying;XIONG Gangqiang(School of Information Engineering,Guangdong Medical University,Zhanjiang 524023,China;Second Clinical Medical College,Southern Medical University,Guangzhou 510515,China;School of Computer Science and Technology,Guangdong University of Technology,Guangzhou 510006,China)
出处 《暨南大学学报:自然科学与医学版》 CAS CSCD 北大核心 2019年第1期85-94,共10页 Journal of Jinan University(Natural Science & Medicine Edition)
基金 国家自然科学基金项目(61170320) 广东省自然科学基金项目(2015A030310178) 广州市科技计划项目(201604016034) 广东省医学科研基金项目(B2018190) 湛江市科技攻关计划项目(2017B01142).
关键词 图像去噪 噪声检测 中值滤波 多邻域中值滤波 image denoising noise detection median filter multi-neighborhood median filter
作者简介 陈家益(1983-),男,讲师,硕士,研究方向:小波分析与图像处理,E-mail:beyond38@163.com;通信作者:战荫伟(1966-),男,教授,博士,硕士生导师,CCF高级会员,研究方向:图像处理、模式识别和计算机视觉,E-mail:ywzhan@gdut.edu.cn.
  • 相关文献

参考文献8

二级参考文献83

  • 1宋宇,李满天,孙立宁.基于相似度函数的图像椒盐噪声自适应滤除算法[J].自动化学报,2007,33(5):474-479. 被引量:35
  • 2郭海霞,解凯.一种改进的自适应中值滤波算法[J].中国图象图形学报,2007,12(7):1185-1188. 被引量:27
  • 3YANG Rui-kang, LIN Yin, GABBOUJ M, et al. Optimal weighted median filtering under structural constraints[J]. IEEE Transactions on Signal Processing, 1995, 43(3): 591-604. 被引量:1
  • 4ALAJLANA N, KAMELA M, JERNIGAN E. Detail preserving impulsive noise removal[J]. Signal Processing: Image Communication, 2004, 19(10): 993-1003. 被引量:1
  • 5LEAH B, NIR S, NAHUM K. Image deblurring in the presence of salt-and-pepper noise[J]. Lecture Notes in Computer Science, 2005, 3459: 107-118. 被引量:1
  • 6CHAN R H, HO Chung-wa, NIKOLOVA M. Salt-and-pepper noise removal by median-type noise detectors and detail-preserving regularization[J]. IEEE Transactions on Image Processing, 2005, 14(10): 1479- 1485. 被引量:1
  • 7KENNY K V T, NOR A M I. Noise adaptive fuzzy switching median filter for salt-and-pepper noise reduction[J]. IEEE Signal Processing Letters, 2010, 17(3):281-284. 被引量:1
  • 8HUANG T S, YANG G J, TANG G Y. Fast two- dimensional median filtering algorithm[J]. IEEE Transactions on Acoustics, Speech, Signal Process, 1979, ASSP-1(1): 13-18. 被引量:1
  • 9WANG Z, ZHANG D. Progressive switching median filter for the removal of impulse noise from highly corrupted images[J]. IEEE Transactions on Circuits System, 1999, 46(1): 78-80. 被引量:1
  • 10HAN W Y, LIN J C. Minimum-maximum exclusive mean (MMEM) filter to remove impulse noise from highly corrupted images[J]. IEEE Electronics Letters, 1997, 33(2): 124-125. 被引量:1

共引文献37

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈