基于区域信息的Snake模型医学图像分割

本文针对Snake模型应用于图像边缘检测时对于噪音过于敏感的不足和易于从弱边界溢出．提出了一种新的约束力。在新的约束力的作用下，Snake模型可以很好地减小噪音的干扰，防止曲线溢出弱边界，并使初始曲线具有更大的选择空间，使模型的分割性能更好。实验证明该模型可以分割出较好的目标边界。

A Medicinal Image Segmentation Method of Snake Model Based on the Region-information

Traditional Snake model is sensitive to the noise of the image and to the position of the initial curve, for it only using the local information. Aiming at this disability, this paper gives a new pressure and with this pressure the Snake model can reduce the effect of the noise and prevent the curve over the weak edge. The improved model can get a better result.