欢迎访问《图学学报》 分享到:

图学学报

• 视觉与图像 • 上一篇    下一篇

基于变动权值的混合水平集图像分割模型

  

  1. 武汉大学数学与统计学院,湖北 武汉 430072
  • 出版日期:2017-12-30 发布日期:2018-01-11
  • 基金资助:
    国家自然科学基金面上项目(11671307)

Hybrid Level Set Image Segmentation Model Based on Variable Weights

  1. School of Mathematics and Statistics, Wuhan University, Wuhan Hubei 430072, China
  • Online:2017-12-30 Published:2018-01-11

摘要: 基于局部区域的活动轮廓模型(LRAC)分割图像时对初始轮廓的严重依赖性,提出
一种基于局部和全局区域结合的水平集图像分割算法。结合Chan-Vese 水平集模型和LRAC 模型
的特点,在构造水平集函数时定义了变动的权值参数,将水平集函数的局部和全局能量泛函项结
合起来,其中,权重参数由图像梯度和图像演化曲线内外局部均值定义。另外,在水平集函数演
化时采用窄带法,以减小计算的时间复杂度。实验结果表明,该算法模型兼有CV 模型和LRAC
模型的优点,比LRAC 模型对初始轮廓选取的依赖性低,收敛速度快;比窄带CV 模型的对目标
边缘分割效果好。

关键词: 水平集, 图像分割, 活动轮廓模型, 混合模型, 窄带法

Abstract: In this paper, a new algorithm of image segmentation based on the combination of the local
region and global region was proposed to solve the dependence of the initial contour on localizing
region-based active contour (LRAC) model. The algorithm combine the characteristics of Chan-Vese
model and LRAC model. When constructing the level set function, the variable weight parameters
were defined to combine the local and global energy functional terms of the level set function. Further,
the weight parameters were defined by image gradient and the mean of the inner and outer pixels at
the local image. In addition, the narrow band method was used in the evolution of the level-set
function to reduce the complexity of computation time. Experimental results show that our model has
the advantages of both CV model and LRAC model. Compared with LRAC model, the method we
proposed relies much less on the initial contour and has a better convergence rate. While compared
with CV model, the precision of our model is higher in the effect of target edge segmentation.

Key words: level set, image segmentation, active counter model, hybrid model, narrow band method