{"title":"实时活动轮廓","authors":"Cheng Jin","doi":"10.1145/1900008.1900073","DOIUrl":null,"url":null,"abstract":"Active contours represent a widely used segmentation technique. Classical developments often involve great algorithmic complexity, inconveniences with local minima and low convergence to boundary concavities. This paper describes an approach based on a Coarse-to-Fine Normal Neighborhoods strategy (CoFiN2) which leads to lower computational costs, being robust to local minima, and encourages convergence to boundary concavities. This approach is compared with classical methods and is applied on Magnetic Resonance Imaging (MRI) in a real time application.","PeriodicalId":333104,"journal":{"name":"ACM SE '10","volume":"71 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"On real time active contours\",\"authors\":\"Cheng Jin\",\"doi\":\"10.1145/1900008.1900073\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Active contours represent a widely used segmentation technique. Classical developments often involve great algorithmic complexity, inconveniences with local minima and low convergence to boundary concavities. This paper describes an approach based on a Coarse-to-Fine Normal Neighborhoods strategy (CoFiN2) which leads to lower computational costs, being robust to local minima, and encourages convergence to boundary concavities. This approach is compared with classical methods and is applied on Magnetic Resonance Imaging (MRI) in a real time application.\",\"PeriodicalId\":333104,\"journal\":{\"name\":\"ACM SE '10\",\"volume\":\"71 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-04-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM SE '10\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/1900008.1900073\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM SE '10","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/1900008.1900073","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Active contours represent a widely used segmentation technique. Classical developments often involve great algorithmic complexity, inconveniences with local minima and low convergence to boundary concavities. This paper describes an approach based on a Coarse-to-Fine Normal Neighborhoods strategy (CoFiN2) which leads to lower computational costs, being robust to local minima, and encourages convergence to boundary concavities. This approach is compared with classical methods and is applied on Magnetic Resonance Imaging (MRI) in a real time application.