首页 | 本学科首页   官方微博 | 高级检索  
     

基于贝叶斯估计自适应软硬折衷阈值Curvelet图像去噪技术
引用本文:杨国梁,雷松泽.基于贝叶斯估计自适应软硬折衷阈值Curvelet图像去噪技术[J].西北纺织工学院学报,2011(6):857-861,866.
作者姓名:杨国梁  雷松泽
作者单位:西安工业大学计算机学院,陕西西安710032
基金项目:基金项目:陕西省教育厅专呒件研基金项目(2010JK595);西安工业大学校长科研基金项目(XGYXJJ1006)
摘    要:针对传统阈值图像去噪方法存在的不足,提出了基于贝叶斯估计和Curvelet变换的软硬折衷阈值图像去噪方法,自适应地对不同的Curvelet子带进行阈值化处理.实验结果表明,该方法对图像中的边缘曲线特征有更好的复原.去噪后图像的峰值信噪比值(PSNR)更高,视觉效果更好.

关 键 词:脊波变换  Curvelet变换  贝叶斯估计  图像去噪

The image denoising method of soft and hard adaptive thresholding based on Curvelet transform and Bayesian estimation
YANG Guo-liang,LEI Song-ze.The image denoising method of soft and hard adaptive thresholding based on Curvelet transform and Bayesian estimation[J].Journal of Northwest Institute of Textile Science and Technology,2011(6):857-861,866.
Authors:YANG Guo-liang  LEI Song-ze
Affiliation:(College of Computer Science and Engineering,Xi′an Technological University,Xi′an 710032,China)
Abstract:According to the defects of soft thresholding and hard thresholding image denoising methods,the image denoising method of soft and hard adaptive thresholding is proposed based on Curvelet transform and Bayesian estimation image denoising.Experiment results show that the new method has the advantages in denoised images with higher quality recovery of edges.It is capable for achieving the higher peak signal-to-noise ratio(PSNR) and giving better visual quality.
Keywords:ridgelet transform  Curvelet transform  Bayesian estimation  image denoising  
本文献已被 维普 等数据库收录!
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