本文通过对图像进行二值化的处理分析，探讨如何选取最合适的阈值来分割图像，采取基于OTSU 算法的单 阈值分割法，根据类间方差最小的原理，能自动选取最佳阈值，使图像的目标部分和背景部分得到最好的分割。

With the analysis of image binary processing, this paper discusses how to select the most appropriate threshold to segment the image. It uses the single Otsu threshold segmentation method which is based on the principle of minimum class variance, to select the best threshold automatically, so that the target and background of the image can get the best segmentation.