小波去噪举例.pdf

4.6 [4] 4.6.1 MATLAB wnoise sqrt_snr=3; init=231434; [x,xn]=wnoise(3,11,sqrt_snr,init); % WNOISE generate noisy wavelet test data. % X= WNOISE(FUN,N) returns values of the test function given by FUN, on a % 2^N sample of [0,1]. [X,XN] = WNOISE(FUN,N,SQRT_SNR) returns the % previous vector X rescaled such that std(x) = SQRT_SNR. The returned % vector XN contains the same test vector X corrupted by an additive Gaussian % white noise N(0,1). Then XN has a signal-to-noise ratio of (SQRT_SNR^2). % [X,XN] = WNOISE(FUN,N,SQRT_SNR,INIT) returns previous vectors X and % XN, but the generator seed is set to INI value. subplot(3,2,1),plot(x) title(original test function) subplot(3,2,2),plot(xn) title(noised function) %2**11 3 lev=5; xd=wden(x,heursure,s,one,lev,sym8); % [XD,CXD,LXD] = WDEN(X,TPTR,SORH,SCAL,N,wname) % returns a de-noised version XD of input signal X obtained by thresholding the % wavelet coefficients. Additional output arguments [CXD,LXD] are the wavelet % decomposition structure of de-noised signal XD. WDEN % [C,L]XDXD % {CXDLXD} % TPTR(contains threshold selection rule)=heursure, % heursure is an heuristic variant of the first option % Stein % SORH (s or h) is for soft or hard thresholding % SCAL(=onedefines multiplicative threshold rescaling:one for no rescaling % wname=sym8 subplot(3,2,3),plot(xd) title(One de-noised function) % sym85 SURE xd=wden(x,heursure,s,sln,lev,sym8); % sln for rescaling using a single estimation % of level noise based on first level coefficients % subplot(3,2,4),plot(xd) title(Sln de-noised function) % sym8SURE xd=wden(x,sqtwolog,s,sln,lev,sym8); % for universal threshold sqrt(2*log(.)) . subplot(3,2,5),plot(xd) title(Sqtwolog de-noi