人工蜂群算法在图像分割中的应用研究

摘要

In order to segment images exactly and quickly, a new method on image segmentation is proposed, which integrates Artificial Bee Colony (ABC) algorithm, gray morphology and two-dimensional Otsu method. In this method, close operation in gray morphology is applied to reduce image noise. Image thresholds are regarded as bees and the fitness function of ABC algorithm is designed by two-dimensional Otsu method. The best threshold is approached in parallel via the division of labor, cooperation and information sharing of employed bees, onlookers and scouts. Experimental results indicate that when the method is applied to infrared image or SAR image, it can provide the consequent analysis and processing with more suited segmented targets.%为快速准确地分割图像,将新型群体智能模型中的人工蜂群算法、灰度形态学和二维Otsu法相结合,提出了一种图像分割新方法.该方法对待分割的图像进行灰度形态学中的闭操作预处理,以抑制图像噪声,把图像阈值看成人工蜂群算法中的蜜蜂,利用二维Otsu法设计人工蜂群算法的适应度函数；通过采蜜蜂、侦察蜂和观察蜂的分工协作和信息共享,逐代逼近最佳阈值.实验结果显示,该方法在分割红外图像和SAR图像时,分离出来的目标更加适合后序的分析和处理.