基于多特征和支持向量机的风景图像分类

摘要

This paper mainly proposed a classification method based on multi features and support vector machine. Firstly, by analyzing the features of landscape image in the visual content, the image is described by means of fusion color, texture and shape features. Secondly, a weighted principal component method is used to reduce the features of high dimensional image. Finally, the experimental results show that the method proposed in this paper has a good classification effect on landscape images.%本文提出了一种基于多特征和支持向量机的风景图像分类方法。首先，通过深入分析风景图像在视觉内容上的显著特点，利用融合颜色、纹理和形状等多种特征的方式来描述图像；其次，采用一种加权主成分方法对提取的高维图像特征进行有效降维；最后，运用基于支持向量机的分类器对图像进行分类。经试验验证，本文中提出的方法对风景图像有较好的分类效果。