计算机应用 ›› 2012, Vol. 32 ›› Issue (01): 245-247.DOI: 10.3724/SP.J.1087.2012.00245

• 图形图像技术 • 上一篇    下一篇

基于符号压力函数的几何活动轮廓模型

杨建功,汪西莉   

  1. 陕西师范大学 计算机科学学院,西安 710062
  • 收稿日期:2011-06-27 修回日期:2011-08-24 发布日期:2012-02-06 出版日期:2012-01-01
  • 通讯作者: 杨建功
  • 作者简介:杨建功(1974-),男,陕西西安人,讲师,硕士,主要研究方向:模式识别、图像处理;汪西莉(1969-),女,陕西西安人,教授,博士,主要研究方向:智能信息处理、模式识别、图像处理。
  • 基金资助:

    中央高校基本科研业务费专项(GK200902015)

Geometric active contour model based on signed pressure force function

YANG Jian-gong,WANG Xi-li   

  1. School of Computer Science, Shaanxi Normal University, Xi'an Shaanxi 710062, China
  • Received:2011-06-27 Revised:2011-08-24 Online:2012-02-06 Published:2012-01-01
  • Contact: YANG Jian-gong

摘要: 针对几何活动轮廓(GAC)模型的诸多缺点,提出一种基于符号压力(SPF)函数的活动轮廓模型。采用一种基于区域统计信息的符号压力函数作为边界指示,能够提高演化曲线在运动过程中对模糊边界的识别能力和抗噪能力。相对于传统几何活动轮廓模型,所提模型具有如下特点:一是能够有效分割边界模糊的目标;二是更具抗噪能力;三是轮廓线运动具有双向性。实验结果表明了所提模型的有效性。

关键词: 图像分割, 几何活动轮廓模型, 水平集, 边界指示函数, 符号压力函数

Abstract: With regard to several drawbacks of Geometric Active Contour (GAC) model, a new active contour model based on Signed Pressure Force (SPF) was proposed in this article. A region-based signed pressure force function was constructed as the edge detector in this model, which made evolving contour more sensitive to blurred edge during evolution and more robust against noise. By contrast with the traditional geometric active contour model, the proposed model has the following advantages: firstly it can segment objects with blurred boundary; secondly, it is more anti-noising; thirdly, the movement of contour is bi-directional. The experimental results show the efficiency of the proposed model.

Key words: image segmentation, Geometric Active Contour (GAC) model, level set, edge detector function, Signed Pressure Force (SPF) function

中图分类号: