计算机工程与应用 ›› 2012, Vol. 48 ›› Issue (27): 147-149.

• 图形、图像、模式识别 • 上一篇    下一篇

选择性自适应水平集演化模型

周  奔,何传江,王  艳   

  1. 重庆大学 数学与统计学院,重庆 401331
  • 出版日期:2012-09-21 发布日期:2012-09-24

Selectively adaptive distance preserving level set evolution model

ZHOU Ben, HE Chuanjiang, WANG Yan   

  1. College of Mathematics and Statistics, Chongqing University, Chongqing 401331, China
  • Online:2012-09-21 Published:2012-09-24

摘要: 自适应距离保持水平集演化模型是在无需初始化模型基础上引入了可变权系数,从而很好地摆脱了演化曲线对初始位置的依赖。该模型存在着一些明显的不足:一是对噪声比较敏感;二是对灰度不均图像分割不准确。基于自适应距离保持水平集演化模型,引入了一个新的可变权系数,据此定义了一个新的边缘停止函数。实验表明,新的自适应距离保持水平集演化模型较好地克服上述两点不足。

关键词: 图像分割, 水平集方法, 选择性自适应演化系数, 梯度选择性边缘停止函数

Abstract: Adaptive distance preserving level set evolution model is derived from level set evolution without re-initialization model, which introduces a variable weight coefficient and so eliminates the need of initial contours. However, this model has the drawbacks of high sensitiveness to noise and locating inaccurately the object edge of image due to intensity inhomogeneity. Following this model, this paper introduces a new variable weight coefficient and a new edge stop function based on this variable weight coefficient. Experimental results show that the distance preserving level set evolution model can really overcome the above-mentioned drawbacks.

Key words: image segmentation, level set method, selective adaptive evolution coefficient, gradient edge stop function of selective