This package contains the Matlab codes for denoisinig greyscale images using
BlockShrink[1] implemented with a decimated wavelet transform. We perform
the wavelet transform using Wavelab 850 toolbox which can be free downloaded
from http://www-stat.stanford.edu/~wavelab/.
This software is non-optimized Matlab codes and provided for non-commercial
and research purposes only. If you find any bugs or have any suggestions,
please contact with me.
References:
[1] Zhou Dengwen and Shen Xiaoliu, "Image denoising using block
thresholding," in Proc. 2008 congress on image and signal
processing,Sanya, Hainan, China，May 2008, pp. 335–338.
Designed by: Zhou Dengwen
zdw@ncepu.edu.cn
Department of Computer Science & Technology
North China Electric Power University(Beijing)(NCEPU)
Filies:
DenoiseFun.m: denoising main function using BlockShrink
SubbandThresholding.m: thresholding the noisy subband
according to BlockShrink rule
Parameters.m: Select the optimal block size and corresponding threshold
Parameters.mexw32: This file is significantly faster than Parameters.m
Calc_MSE_PSNR: computing MSE and PSNR
test: denoising demonstration
Copyright (c) 2008 Zhou Dengwen. All Rights Reserved.
Zhou Dengwen
Jun. 11, 2009 |
