The Savitsky-Golay filter isa smoothing filter based on polynomial regression.Itemploys the regression fitting capacity to improve the smoothing results.But Savit-sky-Golay filter uses a fix sized window.It has the sa...The Savitsky-Golay filter isa smoothing filter based on polynomial regression.Itemploys the regression fitting capacity to improve the smoothing results.But Savit-sky-Golay filter uses a fix sized window.It has the same shortage of Window FourierTransform.Wavelet mutiresolution analysis may deal with this problem.In this paper,tak-ing advantage of Savitsky-Golay filter's fitting ability and the wavelet transform's multiscaleanalysis ability,we developed a new lifting transform via Savitsky-Golay smoothing filteras the lifting predictor,and then processed the signals comparing with the ordinary Savit-sky-Golay Smoothing method.We useed the new lifting in noisy heavy sine denoising.Thenew transform obviously has better denoise ability than ordinary Savitsky-Golay smooth-ing method.At the same time singular points are perfectly retained in the denoised signal.Singularity analysis,multiscale interpolation,estimation,chemical data smoothing andother potential signal processing utility of this new lifting transform are in prospect.展开更多
Field spectrum pretreatment experiments were carried out,and denoising nu- merical experiment via lifting wavelet transform (LWT) was designed,and several famous test signals including blocks,bumps,heavy sine and dopp...Field spectrum pretreatment experiments were carried out,and denoising nu- merical experiment via lifting wavelet transform (LWT) was designed,and several famous test signals including blocks,bumps,heavy sine and doppler were processed via LWT in these experiment.And the field spectrum was processed via LWT.Experiments proved that SNRG'tO-SNRN curves have similar feature and they all have a peak.And SNRG of al- most all employed wavelets have higher value with SNRN between 0 and 20 dB.When sig- nal is at high SNR,the SNRG is very little,and the MSED of denoised signal became little by little.LWT is more suite to denoise the low SNR or heavy noise contaminated signals. Bior4.4 have wider SNRN interval for denoising comparing with other five wavelets,includ- ing haar,db6,sym6,bior2.2 and bior3.3.Original field spectrum is processed by 3 stage liftings based on bior4.4 to denoise the trivial noise-contaminated regions.On processing the water band signal,logarithm transform is firstly taken.And then the spectrum is de- noised via LWT based on bior4.4.The results show that an excellent denoised spectrum can be get,especially between 350 nm and 1 800 nm,and between 1 960 nm to 2 500 nm While there is still a bump around 1 900 nm,this maybe due to the spectrum machine's limited precision.展开更多
基金Supported by Land and Resource Ministry of China(30302408-3)
文摘The Savitsky-Golay filter isa smoothing filter based on polynomial regression.Itemploys the regression fitting capacity to improve the smoothing results.But Savit-sky-Golay filter uses a fix sized window.It has the same shortage of Window FourierTransform.Wavelet mutiresolution analysis may deal with this problem.In this paper,tak-ing advantage of Savitsky-Golay filter's fitting ability and the wavelet transform's multiscaleanalysis ability,we developed a new lifting transform via Savitsky-Golay smoothing filteras the lifting predictor,and then processed the signals comparing with the ordinary Savit-sky-Golay Smoothing method.We useed the new lifting in noisy heavy sine denoising.Thenew transform obviously has better denoise ability than ordinary Savitsky-Golay smooth-ing method.At the same time singular points are perfectly retained in the denoised signal.Singularity analysis,multiscale interpolation,estimation,chemical data smoothing andother potential signal processing utility of this new lifting transform are in prospect.
文摘Field spectrum pretreatment experiments were carried out,and denoising nu- merical experiment via lifting wavelet transform (LWT) was designed,and several famous test signals including blocks,bumps,heavy sine and doppler were processed via LWT in these experiment.And the field spectrum was processed via LWT.Experiments proved that SNRG'tO-SNRN curves have similar feature and they all have a peak.And SNRG of al- most all employed wavelets have higher value with SNRN between 0 and 20 dB.When sig- nal is at high SNR,the SNRG is very little,and the MSED of denoised signal became little by little.LWT is more suite to denoise the low SNR or heavy noise contaminated signals. Bior4.4 have wider SNRN interval for denoising comparing with other five wavelets,includ- ing haar,db6,sym6,bior2.2 and bior3.3.Original field spectrum is processed by 3 stage liftings based on bior4.4 to denoise the trivial noise-contaminated regions.On processing the water band signal,logarithm transform is firstly taken.And then the spectrum is de- noised via LWT based on bior4.4.The results show that an excellent denoised spectrum can be get,especially between 350 nm and 1 800 nm,and between 1 960 nm to 2 500 nm While there is still a bump around 1 900 nm,this maybe due to the spectrum machine's limited precision.
