Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (25): 157-159.DOI: 10.3778/j.issn.1002-8331.2010.25.046

• 图形、图像、模式识别 • Previous Articles     Next Articles

Image denoising method with improved NeighLevel

SHANG Zhao-wei1,2,ZHAI Zhen-xing1,PANG Qing-kun1,ZHAO Zheng-hui1,LI Jian1,YANG Jian-wei3   

  1. 1.College of Computer Science,University of Chongqing,Chongqing 400030,China
    2.Key Laboratory of Pattern Recognition and Intelligent Information Processing,Chengdu 610106,China
    3.College of Mathematics and Physics,Nanjing University of Information Engineering,Nanjing 210044,China
  • Received:2010-05-10 Revised:2010-07-08 Online:2010-09-01 Published:2010-09-01
  • Contact: SHANG Zhao-wei

改进的NeighLevel图像去噪方法

尚赵伟1,2,翟振兴1,庞庆堃1,赵正辉1,李 剑1,杨建伟3   

  1. 1.重庆大学 计算机学院,重庆 400030
    2.四川省模式识别与智能信息处理重点实验室,成都 610106
    3.南京信息工程大学 数理学院,南京 210044
  • 通讯作者: 尚赵伟

Abstract: For the limitations of image information representation of complex wavelet transform and neighborhood correlation description depiction by NeighLevel,an improved image denoising method is presented.First of all,characters of the direction number selected freely for non-aliasing of non-aliasing contourlet are used,the image edge details are expressed,and the deficiency of complex wavelet for direction information is overcome;then the expression ability is improved by neighborhood information through the mutual information of neighborhood wavelet coefficients.Theoretical analysis and experimental results show that its peak signal to noise ratio increases by 0.6%~7% when the variance of image noise is between 30 and 60 compared to the method named CWT-NeighLevel,meanwhile a better visual result is maintained in the aspect of the edge feature.

Key words: image denoising, non-aliasing contourlet transform, mutual information

摘要: 针对复小波变换在图像方向信息表征和NeighLevel算法刻画邻域相关性的局限性,提出了一种改进的图像去噪方法。首先,利用抗混叠轮廓波自由选择方向数的特点,能更好地提取图像边缘细节,克服了复小波方向性信息表达的不足;然后用变换域邻域小波系数之间的互信息量,改进NeighLevel方法对邻域信息的表达能力。理论分析和实验结果表明,与CWT-NeighLevel相比,在噪声方差等于30~60时,峰值信噪比提高了0.6%~7.0%,且在边缘特征方面保持了良好的视觉效果。

关键词: 图像去噪, 抗混叠轮廓波变换, 互信息量

CLC Number: