An algorithm of suppressing image noise based on the integration of wavelet threshold function and improved median filter
For the presence of salt-and-pepper noise and Gaussian noise in image processing,an algorithm of suppressing image noise is proposed based on the integration of wavelet threshold function and improved median filter.Based on the significant differences of pixel grayscale values between the salt-and-pepper noise and its surroundings,the saltand-pepper noise and take the 3 × 3 template iterative filter out salt-and-pepper noise are estimated.To processing Gaussian noise a new threshold function of using the thought of limit is proposed.Three control variables are used.By used control variables the new composition of the wavelet coefficients infinitely is closed to the original wavelet coefficients within a certain threshold range.Experimental results show that the peak signal to noise ratio (PSNR) is increased and the mean square error (MSE) is decreased,image detail preserved is better.
mixed noiseimproved median filterwavelet thresholdpeak signal to noise ratio (PSNR)
NETL
NSTL
万方数据
维普
