基于多目标蜂群优化的阈值图像分割算法

Image thresholding segmentation based on multi-objective artificial bee colony optimization

为把图像的目标与背景准确地分割开来,将多目标人工蜂群算法引入到多阈值图像分割,提出了一种新的阈值图像分割算法。该算法首先将阈值看做人工蜂群算法中的蜜源,利用类间方差和最大熵原理两个准则作为多目标人工蜂群算法的适应度函数,然后在引领蜂和跟随蜂阶段引入精英解来参与蜜源位置更新,使得算法更有效地逼近最佳阈值,最后采用类间差异和类内差异的加权比值来选取最优解。实验结果表明,该算法能够取得较好的分割结果。

In order to accurately segment the targets and background in images,a multi-objective artificial bee colony algorithm is introduced into the multi-thresholding image segmentation problem and then a novel image segmentation algorithm is proposed in this paper. Firstly,the thresholds are regarded as the honey source in the artificial bee colony algorithm,and the interclass variance and entropy are adopted as the fitness functions of the multi-objective artificial bee colony algorithm. Then,the elite solution is introduced into the employed bee and onlooker bee phase to participate in the position updating,which makes the algorithm approximate the optimal thresholds more effectively. Finally,the weighted ratio of between-cluster variation and intra-cluster variation is adopted to select an optimal solution. Experimental results show that the algorithm can obtain good segmentation results.