简介：

简介：Imagedenoisingisthebasicproblemofimageprocessing.Quaternionwavelettransformisanewkindofmultiresolutionanalysistools.Imageviaquaternionwavelettransform,waveletcoefficientsbothinintrascaleandininterscalehavecertaincorrelations.First,accordingtothecorrelationofquaternionwaveletcoefficientsininterscale,non-Gaussiandistributionmodelisusedtomodelitscorrelations,andthecoefficientsaredividedintoimportantandunimportancecoefficients.Thenweusethenon-Gaussiandistributionmodeltomodeltheimportantcoefficientsanditsadjacentcoefficients,andutilizetheMAPmethodestimateoriginalimagewaveletcoefficientsfromnoisycoefficients,soastoachievethepurposeofdenoising.Experimentalresultsshowthatouralgorithmoutperformstheotherclassicalalgorithmsinpeaksignal-to-noiseratioandvisualquality.