基于微粒群算法的OTSU图像分割方法

OTSU Image Segmentation Method Based On Particle Swarm Optimization Algorithm

本文研究了图像闽值分割方法中常用的OTSU算法，在此基础上提出了基于微粒群算法的OTSU图像分割方法，该方法利用微粒群算法的快速全局寻优，确定图像的分割闯值所对应的灰度值，在该灰度值下目标和背景的方差最大。实验中选用了像素分别是8位和16位的两幅图片来进行分割，得到了较好的分割效果，而且该方法大大提高了计算速度，是一种有效的图像分割方法。

The paper researches the OTSU algorithm, which is commonly used in the image threshold segmentation method. On the basis of this method, the paper presents the OTSU image segmentation method based on particle swarm algorithm. This method uses the rapid global optimization of the PSO algorithm, and determines the corresponding gray-scale value of image segmentation threshold, in which there is the greatest variance between the targets and background in the picture. In the experiment, the two pictures with 8 and 16 bit pixels respectively were used to segment, obtained the good image segmentation results, and this method has greatly enhanced the speed of calculation, it is an effective method of image segmentation.