two-stage image segmentation based on edge and region information

two-stage image segmentation based on edge and region information

ID:10665388

大小:50.00 KB

页数:14页

时间:2018-07-07

two-stage image segmentation based on edge and region information_第1页
two-stage image segmentation based on edge and region information_第2页
two-stage image segmentation based on edge and region information_第3页
two-stage image segmentation based on edge and region information_第4页
two-stage image segmentation based on edge and region information_第5页
资源描述:

《two-stage image segmentation based on edge and region information》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、Two-stageimagesegmentationbasedonedgeandregioninformationJournalofHarbinInstituteofTechnolo(NewSeries),Vo1.14,No.4,2007Two-stageimagesegmentationbasedonedgeandregioninformationRANXin.QIFei—hu冉鑫,戚飞虎(1.MerchantMarineCollege,ShanghaiMaritimeUniversity,Shanghai20

2、0135,China,E—mail:simonran@sjtu.edu.cn2.Dept.ofComputerScienceandEngineering,ShanghaiJiaotongUniversity,Shahghai200030,China)Abstract:Atwo—stagemethodforimagesegmentationbasedonedgeandregioninformationisproposed.Differ-entdeformationschemesareusedattwostagesf

3、orsegmentingtheobjeetcorrectlyinimageplane.Atthefirststage,thecontourofthemodelisdividedintoseveralsegmentshierarchicallythatdeformrespectivelyusingaf-finetransformation.Afterthecontourisdeformedtotheapproximateboundaryofobject,afinematchmecha—nismusingstatis

4、ticalinformationoflocalregiontoredefinetheexternalenergyofthemodelisusedtomakethecontourfittheobject~boundaryexactly.Thealgorithmiseffective,asthehierarchicalsegmentaldeformationmakesuseoftheglobeandlocalinformationoftheimage,theaffinetransformationkeepstheco

5、nsistencyofthemodel,andthereformativeapproachesofcomputingtheinternalenergyandexternalenergyareproposedtore—ducethealgorithmcomplexity.Theadaptivemethodofdefiningthesearchareaatthesecondstagemakesthemodelconvergequickly.Theexperimentalresultsindicatethatthepr

6、oposedmodeliseffectiveandrobusttolo—calminimaandabletosearchforconcaveobjects.Keywords:activecontourmodel;regiongrowing;imagesegmentation;affinetransformationCLCnumber:TP391Documentcode:AArticleID:1005—9113(2007)04-0533-08Activecontourmodels,alsoknownassnakes

7、…,areenergy—mi'ni'mi'zi'ngsplinesthatcandeformtofitim—agefeaturesundertheinternalforcescomingfromwith.inthecontouritselfandexternalforcescomputedfromtheimagedata.Asactivecontourmodelsutilizetheglobalconstraintsandkeepsmoothandcontinuousdur—ingdeformation,they

8、canextracttheobject~boundarycorrectlyevenwhenlocalboundaryisweakordiscon—nected.Now,activecontourmodelshavebeenusedextensivelyinimageanalysis,videosegmentationandtracking['.andbiomedicala

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。