预览加载中，请您耐心等待几秒...

结合边缘信息的二维Otsu阈值分割算法研究.docx

预览
1/2
2/2

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

结合边缘信息的二维Otsu阈值分割算法研究 Abstract TheOtsuthresholdingalgorithmisacommonlyusedmethodforimagesegmentation.Itcalculatesathresholdthatseparatesforegroundandbackgroundpixelsintheimage.However,ithaslimitationswhenitcomestoimageswithcomplexbackgroundsandoverlappingobjects.Thispaperproposesatwo-dimensionalOtsuthresholdingalgorithmthatincorporatesedgeinformationtoimprovesegmentationperformance.ExperimentalresultsshowthattheproposedalgorithmoutperformstraditionalOtsuthresholdingintermsofaccuracyandrobustness. Introduction Imagesegmentationplaysacriticalroleinimageanalysisandcomputervisionapplications.Thresholdingisawidelyusedsegmentationmethodthatdividespixelsintotwoclassesbasedontheirintensityvalues.TheOtsuthresholdingalgorithmisapopularmethodthatcalculatesathresholdthatminimizesthevariancebetweenthetwoclassesofpixels.However,thisalgorithmhaslimitationswhenitcomestoimageswithcomplexbackgroundsandoverlappingobjects.Theedgesofobjectscontainimportantinformationthatcanbeusedtoimprovesegmentationaccuracy.Thispaperproposesatwo-dimensionalOtsuthresholdingalgorithmthatincorporatesedgeinformationtoovercomethelimitationsoftraditionalOtsuthresholding. RelatedWork TherehavebeenmanystudiesonimprovingtheperformanceoftheOtsuthresholdingalgorithm.Forexample,Chenetal.proposedafuzzyOtsuthresholdingalgorithmthatincorporatesfuzzylogictohandleimageswithnoise.Weietal.proposedamulti-Otsuthresholdingalgorithmthatsegmentsimagesintomultipleclasses.Xuetal.proposedadynamicthresholdingalgorithmthatadaptstothelocalcharacteristicsoftheimage.However,fewstudieshaveexploredincorporatingedgeinformationintotheOtsuthresholdingalgorithm. ProposedMethod TheproposedalgorithmusestheSobeloperatortodetectedgesintheimage.TheSobeloperatorisawidelyusededgedetectionmethodthatcalculatesthegradientoftheimageintensity.Thegradientrepresentstherateofchangeoftheintensity,whichishighattheedgesofobjects.TheedgesdetectedbytheSobeloperatorareusedtoguidethethresholdingprocess. Theproposedalgorithmworksasfollows: 1.Computethegradientim