计算机工程 ›› 2011, Vol. 37 ›› Issue (21): 120-123.doi: 10.3969/j.issn.1000-3428.2011.21.041

• 人工智能及识别技术 • 上一篇    下一篇

人工分割基元模型

刘 翔1a,徐 琪1b,刘 升2   

  1. (1. 上海工程技术大学 a. 电子电气工程学院;b. 管理学院,上海 201620; 2. 上海海事大学信息工程学院,上海 200135)
  • 收稿日期:2011-05-16 出版日期:2011-11-05 发布日期:2011-11-05
  • 作者简介:刘 翔(1972-),男,讲师、博士研究生,主研方向:图像处理,人工智能;徐 琪,讲师、博士;刘 升,教授、博士
  • 基金项目:
    国家自然科学基金资助项目(61075115)

Artificial Segmentation Element Model

LIU Xiang   1a, XU Qi   1b, LIU Sheng   2   

  1. (1a. College of Electronic and Electrical Engineering; 1b. College of Management, Shanghai University of Engineering Science, Shanghai 201620, China; 2. College of Information Engineering, Shanghai Maritime University, Shanghai 200135, China)
  • Received:2011-05-16 Online:2011-11-05 Published:2011-11-05

摘要: 图像分割过程中存在过度分割和分割不足的问题。为此,提出一种人工分割基元模型。赋予生命个体独立的大小和结构信息,以对应图像局部结构特征,定义独立的个体行为规则,使生命体更具智能性,结合生命整体行为规则和区域增长方法,模拟领地占领的过程,从而实现图像分割。实验结果表明,该模型具有较强的自适应性和鲁棒性。

关键词: 图像分割, 人工生命, 人工分割基元, 行为规则, 领地占领, 区域增长

Abstract: This paper presents an artificial segmentation element model to solve the problems of over-segmentation and under-segmentation of Image. The model is given the information of size and structure individually, which indicates the local structural feature of Image. Individual behavior rules are defined, thus the vital body is more intelligent than others. Image segmentation is accomplished by simulating the process of territory occupied and combining the behavior rule of overall life and the thinking of region growing. Experimental results show that, this model has good self-adaption and robustness.

Key words: image segmentation, artificial life, artificial segmentation element, behavior rule, territory occupied, region growing

中图分类号: