全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

一种新的正则化粒子滤波图像恢复算法

Keywords: 粒子滤波,图像恢复,采样重要性重采样,正则化重采样,混合噪声,乘性噪声,累积分布函数

Full-Text   Cite this paper   Add to My Lib

Abstract:

引入粒子滤波对解决非线性非高斯模型的优良特性,将一种新的正则化粒子滤波算法(regularizedparticlefilter)应用到混合噪声和乘性噪声图像恢复中.由于采样重要性重采样(SIR)方法在重采样时没有考虑观测量而引入误差,本文方法从后验连续分布中采样,引入观测量进而减少误差,同时将易实现的累积分布函数和正则化重采样步骤融合,进一步使粒子方差最小化,解决粒子衰竭问题,缓解退化现象.通过对具有混合噪声图像以及医学乘性噪声图像的恢复效果表明了该算法的有效性,且与小波阈值法和SIR粒子滤波法对

References

[1]  Gonzalez R C,Woods R E,Digital image processing,Beijing:Publishing House of Electronics Industry,2004.
[2]  Arulampalam M S,Maskell S,Gordon N,A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking,IEEE Transactions on Signal Processing,2002(2).
[3]  Fredrik Gustafsson,Fredrik Gunnarsson,Niclas B,Particle filters for position,navigation and tracking,IEEE Transactions on Signal Processing,2002(2).
[4]  Tian Hui,Shen Tingzhi,Hao Bing,Image restoration based on adaptive MCMC particle filter,Piscataway,NJ,USA,2009.
[5]  Rao D,Swamy M,Plotkin E,Image restoration using an hybrid approach based on DWT and SMKF,Thessaloniki,Greece,2001.
[6]  Donoho D L,Denoising by soft thresholding,IEEE Transactions on Information Theory,1995(3).
[7]  Donoho D L,Johnstone I M,Adapting to unknown smoothness via wavelet shrinkage,Journal of the American Statistical Association,1995(90).

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133