N. Paragios, O. Mellina-Gottardo, Visvanathan Ramesh
{"title":"Gradient vector flow fast geodesic active contours","authors":"N. Paragios, O. Mellina-Gottardo, Visvanathan Ramesh","doi":"10.1109/ICCV.2001.937500","DOIUrl":null,"url":null,"abstract":"This paper proposes a new front propagation flow for boundary extraction. The proposed framework is inspired by the geodesic active contour model and leads to a paradigm that is relatively free from the initial curve position. Towards this end, it makes use of a recently introduced external boundary force, the gradient vector field that refers to a spatial diffusion of the boundary information. According to the proposed flow, the traditional boundary attraction term is replaced with a new force that guides the propagation to the object boundaries from both sides. This new geometric flow is implemented using a level set approach, thereby allowing dealing naturally with topological changes and important shape deformations. Moreover the level set motion equations are implemented using a recently introduced numerical approximation scheme, the Additive Operator Splitting Schema (AOS) which has a fast convergence rate and stable behavior. Encouraging experimental results are provided using real images.","PeriodicalId":429441,"journal":{"name":"Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"115","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCV.2001.937500","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 115
Abstract
This paper proposes a new front propagation flow for boundary extraction. The proposed framework is inspired by the geodesic active contour model and leads to a paradigm that is relatively free from the initial curve position. Towards this end, it makes use of a recently introduced external boundary force, the gradient vector field that refers to a spatial diffusion of the boundary information. According to the proposed flow, the traditional boundary attraction term is replaced with a new force that guides the propagation to the object boundaries from both sides. This new geometric flow is implemented using a level set approach, thereby allowing dealing naturally with topological changes and important shape deformations. Moreover the level set motion equations are implemented using a recently introduced numerical approximation scheme, the Additive Operator Splitting Schema (AOS) which has a fast convergence rate and stable behavior. Encouraging experimental results are provided using real images.