Multiwavelets domain singular value features for image texture classification

在线阅读 下载PDF 导出详情
摘要 Anewapproachbasedonmultiwaveletstransformationandsingularvaluedecomposition(SVD)isproposedfortheclassificationofimagetextures.LowersingularvaluesaretruncatedbasedonitsenergydistributiontoclassifythetexturesinthepresenceofadditivewhiteGaussiannoise(AWGN).Theproposedapproachextractsfeaturessuchasenergy,entropy,localhomogeneityandmax-minratiofromtheselectedsingularvaluesofmultiwaveletstransformationcoefficientsofimagetextures.Theclassificationwascarriedoutusingprobabilisticneuralnetwork(PNN).Performanceoftheproposedapproachwascomparedwithconventionalwaveletdomaingraylevelco-occurrencematrix(GLCM)basedfeatures,discretemultiwaveletstransformationenergybasedapproach,andHMMbasedapproach.Experimentalresultsshowedthesuperiorityoftheproposedalgorithmswhencomparedwithexistingalgorithms.
机构地区 不详
出版日期 2007年04月14日(中国期刊网平台首次上网日期,不代表论文的发表时间)
  • 相关文献