基于遗传算法的图像阈值分割研究

Study on image threshold segmentation based on genetic algorithm

主要论述了利用遗传算法进行图像阈值分割的实现方法,重点研究了最大熵和最大类间方差2种阈值分割方法。将通信电源配电屏开关图片作为研究对象,分别采用基于传统搜索算法和遗传算法的最大熵和最大类间方差法对其灰度图进行阈值分割,并应用V isual C++编程实现。实验结果表明,基于遗传算法的最大类间方差法的分割效果好,更好地满足了通信设备对远程视频监控与识别系统中图像分割实时性的需求。

This paper discusses the implementation means of image threshold segmentation based on genetic algorithm and the maximum entropy and Otsu threshold segmentation methods. By studying the switch image of communication power supply distribution screen, it introduces the threshold segmentation for gray image by using maximum entropy and Otsu methods based on traditional search and genetic algorithm together with the programs of Visual C＋＋ software. The results show that this method can satisfy the demands of real-time image segmentation in remote video monitoring and recognition system.