首页|A NEW DEFORMABLE MODEL USING LEVEL SETS FOR SHAPE SEGMENTALTION
A NEW DEFORMABLE MODEL USING LEVEL SETS FOR SHAPE SEGMENTALTION
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
万方数据
In this paper,we present a new deformable model for shape segmentation,which makes two modifications to the original level set implementation of deformable models.The modifications are motivated by difficulties that we have encountered in applying deformable models to segmentation of medical images.The level set algorithm has some advantages over the classical snake deformable models.However,it could develop large gaps in the boundary and holes within the objects.Such boundary gaps and holes of objects can cause inaccurate segmentation that requires manual correction.The proposed method in this paper possesses an inherent property to detect gaps and holes within the object with a single initial contour and also does not require specific initialization.The first modification is to replace the edge detector by some area constraint,and the second modification utilizes weighted length constraint to regularize the curve under evolution.The proposed method has been applied to both synthetic and real images with promising results.
Image segmentationLevel setsConstraintDeformable model
He Ning、Zhang Peng、Lu Ke
展开 >
School of Mathematical Sciences,Capital Normal University,Beijing 100037,China
College of Computing ＆ Communication Engineering, Graduate University of Chinese Academy of Sciences,Beijing 100049,China
NETL
NSTL
万方数据
