严重椒盐噪声污染图像的非线性滤波算法

被引:15
作者
董继扬
张军英
机构
[1] 西安电子科技大学雷达信号处理国家重点实验室
关键词
椒盐噪声; 滤波算法; 灰度图像; 严重污染图像;
D O I
10.16136/j.joel.2003.12.023
中图分类号
TN911.73 [图像信号处理];
学科分类号
摘要
针对灰度图像的椒盐噪声滤波问题,提出一种保细节的非线性滤波算法。利用局部统计信息,首先将图像像素点粗分为信号点、可能的正噪声点和可能的负噪声点3类,建立噪声标矩阵;然后再根据噪声标记矩阵的局部统计信息,将可能的噪声点细分为信号点、噪声点和不确定点3种类别,并分别采用不同的方法进行滤波,以保留更多的图像细节。结果表明,本文算法在去噪能力、自适应性以及保留细节等方面都明显比其它4种算法强,尤其是对于噪声高度污染图像的情况。
引用
收藏
页码:1336 / 1339
页数:4
相关论文
共 10 条
  • [1] AnewdenoisingmethodaboutCMOSimaginingchip. RAORuijian,LAIXinquan,LIYushan. 光电子.激光 . 2001
  • [2] TSun,YNeuvo.Detail preservingmedianbasedfiltersinimageprocessing. PatternRecognit.Lett . 1994
  • [3] W Han,J Lin.Minimum-maximum exclusive mean (MMEM) filter to remove impulse noise from highly corrupted images. Electronics Letters . 1997
  • [4] How-Lung Eng,Kai-Kuang Ma.Noise adaptive softswitching median filter. IEEE Transactions on Image Processing . 2001
  • [5] XING Cang-ju,WANG Shou-jue,DENG Hao-jiang,et al.A new filtering algorithm based on extremumand median value. International Journal of Image and Graphics . 2001
  • [6] E Abreu,M Lightsone,S K Mitra,et al.A new efficient approach for the removal of impulse noise from highly corrupted images. IEEE Transactions on Image Processing . 1996
  • [7] S J Ko,S J Lee.Center weighted median filters and their applications to image enchancement. IEEE Transactions on Circuits and Systems . 1991
  • [8] D Florencio,RSchafer.Decision-based medianfilter usinglocal sig-nal statisties. SPIEInt Symp Visual Communications Image Pro-cessing . 1994
  • [9] D Brownrigg.The weighted median filter. Commun .Assoc . Computer . 1984
  • [10] ZWang,DZhang.Progressiveswitchingmedianfilterfortheremovalofimpulsenoiefromhighlycorruptedimages. IEEETrans.Circuitsandsystems—Ⅱ:analoganddigitalsignalprocessing . 1999