一种基于支持向量机的轴承表面缺陷检测方法

提出了一种基于支持支持向量机和主成分分析的轴承表面缺陷检测算法,该算法把轴承中的非缺陷区域和缺陷区域分别看作两种不同的纹理模式,先利用主成分分析法(PCA)对图像进行降维处理,然后用支持向量机方法对降维后的样本采样学习,然后进行分类判断.实验结果表明,该算法能够较好地实现轴承缺陷的检测分类,有一定的实用价值.

A algorithm of Bearing Defects Detection Based on Support Vector Machines

This paper expoles an algorithm about dearing surface defects detection by Support Vector Machines and principal component analysis that is the new branch of machine learning,in which the defective area and non-defective area are treated as two different textures and are sampled respectively to be learned,in order to reduce dimension,the image data can be processed by PCA.It is shown that this algorithm works well in defects detection.