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: 

• N945.12