一种改进的活动区域轮廓模型--无需水平集重新初始化

New active region contour model without re-initialization

基于区域的活动区域模型已经成功应用在图像分割、目标跟踪等领域,较之基于梯度的活动轮廓模型具有很多优点。但是,这些水平集模型在演化过程中,为了保持为符号距离函数,必须对其重新初始化,降低了曲线演化速度,增加了实现复杂度。为了解决重新初始化问题,在测地活动区域模型的能量函数中,加入惩罚项来约束水平集保持为符号距离函数,无需再重新初始化,极大地提高了演化速度。将其运用在纹理图像、脑MR图像分割以及视频跟踪中,实验证明该模型是有效的。

Active region contour model has been successfully applied in image segmentation,object tracking,etc,which has many pros compared with active contour model based on edge.But,during the evolution of level set,it＇s numerically necessary to keep the evolving level set function close to a signed distance function.Re-initialization,a technique for periodically re-initializing the level set function to a signed distance function during the evolution,results in slowing speed of evolution,increasing complex of implement.To overcome the re-initialization,the author proposes to add a panelized energy into active region contour model to keep level set close to a signed distance function;it thus speeds up the curve evolution and the segmentation.The auhtor applies the model to segment the texture image,brain MRI and track objects;the experiments prove the model is effective.