Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (24): 160-162.

• 图形、图像、模式识别 • Previous Articles     Next Articles

RSF model with linear regularization item

ZHANG Shaohua1,2   

  1. 1.Department of Mathematics,Zunyi Normal College,Zunyi,Guizhou 563002,China
    2.College of Mathematics and Statistics,Chongqing University,Chongqing 401331,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-08-21 Published:2011-08-21

带线性正则化项的RSF模型

张少华1,2   

  1. 1.遵义师范学院 数学系,贵州 遵义 563002
    2.重庆大学 数学与统计学院,重庆 401331

Abstract: RSF(Region-Scalable Fitting) model is able to deal with intensity inhomogeneity;however,it is sensitive to initialization and noise.Therefore,using the theories probe and experiment,the method of combining,based on RSF model,adding a level set linear regularization item,this paper proposes a novel active contour model.This model can address the segmentation of images with intensity inhomogeneity,while it allows for flexible initialization of the contours and is significantly less sensitive to noise.

Key words: image segmentation, active contour, Region-Scalable Fitting(RSF) model, partial differential equation, regularization item

摘要: RSF(Region-Scalable Fitting)模型能够分割灰度不均一图像,但对活动轮廓的初始化和噪声较为敏感。运用理论探究与实验相结合的方法,基于RSF模型,添加一个新的水平集线性正则化项,得到了一个新的活动轮廓模型。实验表明,该模型能够分割灰度不均一图像,对初始轮廓的大小和位置不敏感,抗噪性也较强。

关键词: 图像分割, 活动轮廓, 可缩放区域拟合(RSF)模型, 偏微分方程, 正则化项