基于类间最大方差法的铁谱磨粒彩色图像自动分割

Auto- segmentation of Ferrograph Wear Particle Color Image Based on Maximum- variance Algorithm in All Classes

在磨粒图像RGB彩色空间，选择其3个正交彩色特征，应用类间最大方差法对其分割，依据Fisher判别函数选择其最佳特征与最佳阈值，实现了磨粒彩色图像的分割。大量磨粒图像分割实践证明，该分割方法具有分割精度较高、计算速度快、自适应性强等特点，是铁谱磨粒彩色图像自动分割较理想方法之一。

In the RGB color space of wear particle color image, three vertical - intersecting characters are chosen, its images are segmented by using maximum - variances algorithm in all classes, and its best character and best threshold are chosen by Fisher differentiating function. It is proved that the approach has high segmentation precision, fast computer velocity and self- adaptive ability, and it is a ideal method of wear particle color image auto - segmentation.