数字图像的纹理特征提取与分类研究

本文提出了一种基于Gabor小波和灰度共生矩阵进行数字图像特征提并与支持向量机模型相结合的纹理分类算法。首先分别利用Gabor变换和灰度共生矩阵提取数字图像的特征,进而利用支持向量机算法实现图像的训练和分类。实验结果表明,与传统的分类方法相比,这种通过Gabor小波和灰度共生矩阵得到数字图像的特征并与支持向量机相结合的方法能有效地提高分类正确率。

Textural feature extraction and classification study research of digital image

This paper presents a texture classification algorithm using Gabor wavelet and Gray Level Co-occurrence Matrix as feature extraction method and Support Vector Machine as classifier.First,Gabor transform and Gray Level Co-Occurrence Matrix are used to get the features of the digital images,and then SVM classifiers are followed to build image and realize classification.The experimental results have shown that the methods described in this paper can be more effectively improve the rate of correct classification than the traditional method of classification.