支持向量机(svM)是一种新的机器学习技术。本文采用一对一方法构建多分类SVM

分类器。利用常用的灰度共生矩阵方法提取图像纹理特征，组成特征向量，输入构建好的SVM

多分类器中进行分类。对从Brodatz纹理库中选取的4张纹理图像进行了分类实验，取得较好的

分类结果-Support vector machine (svM) is a new machine learning techniques. In this paper, one way to build a multi-classification SVM classifier. GLCM using methods commonly used to extract image texture features, compositions of the vector input to build a good classifier in the SVM multi-classification. From the Brodatz texture library texture selected four images were classified experiments to obtain better classification results