自适应多阈值图像分割算法  

An Adaptive Multi Threshold Image-Segmentation Algorithm

作　　者：张伟[1] 蒋宏[1] 任章[1] 

机构地区：[1]北京航空航天大学自动化科学与电气工程学院,北京100083

出　　处：《自动化技术与应用》2007年第8期71-73,96,共4页Techniques of Automation and Applications

摘　　要：本文提出了一种新的自适应多阈值图像分割算法。它首先利用势基函数对一维灰度直方图拟合,通过势函数聚类自动确定划分类数;然后在灰度共生矩阵的基础上,依据形状连通度准则,求得使形状连通度最大的一组分割阈值;最后按该组分割阈值执行多阈值图像分割。理论分析和实验结果都表明该算法较传统阈值分割算法优越,具有运算速度快、划分效果好、抗干扰性强的特点。This paper presents a new adaptive multi-threshold segmentation algorithm. Firstly, the 1-D graylevel histogram of the image is fitted by potential base function and the classification number is then determined by clustering; secondly, the multi segmentation thresholds are obtained based on the graylevel co-occurrence matrix. Both theoretical analysis and simulation results indicate that the performance of this new adaptive multi threshold segmentation algorithm is superior to that of the conventional threshold segmentation algorithms.

关 键 词：图像分割 多阈值 势函数聚类 灰度共生矩阵 形状连通度 

分 类 号：TP291.41[自动化与计算机技术—检测技术与自动化装置]