摘要
为了实现图像的自适应多级分割,利用混沌动力学系统对初值的敏感性和全局耦合映象混沌同步的特点,提出了一种基于耦合映象格子的图像分割方法。方法对每个灰度等级构建全局耦合映象,建立灰度等级间关系矩阵和灰度等级更新模型,通过全局耦合映象混沌同步过程完成灰度等级的自适应聚类。实验结果表明方法对中间类灰度等级聚类具有很好的鲁棒性,分割过程不需要人工干预,并且具有较强的灵活性,优于阈值分割和边缘检测的图像分割方法。
In order to carry out adaptive multithreshold image segmentation, based on sensitive dependence on initial conditions of chaotic dynamic system and chaotic synchronization feature of globally coupled map in coupled map lattice, this paper put forward a new image segmentation method based on coupled map lattice. The method constructs the globally coupled map for each gray level, makes the correlation matrix between gray levels and the update model of each gray level and accomplishes the adaptive clustering of gray level through chaotic synchronization process of globally coupled map. The experiments results show that the method is robust enough to cluster ambiguous elements, not need to be intervened in segment process and has better flexibleness,which is superior to the threshold segment method and the edge detection method.
出处
《激光与红外》
CAS
CSCD
北大核心
2009年第12期1344-1347,共4页
Laser & Infrared
基金
国家自然科学基金项目(No.60572160)资助
关键词
图像分割
耦合映象格子
全局耦合映象
混沌同步
image segmentation
coupled map lattice
globally coupled map
chaotic synchronization
