| 用支持向量机实现尺度和旋转不变性纹理分类 |
| |
| 引用本文： | 蒋金山,余英林. 用支持向量机实现尺度和旋转不变性纹理分类[J]. 华南理工大学学报(自然科学版), 2004, 32(5): 26-29,33 |
| |
| 作者姓名： | 蒋金山 余英林 |
| |
| 作者单位： | 华南理工大学,电子与信息学院,广东,广州,510640;华南理工大学,电子与信息学院,广东,广州,510640 |
| |
| 摘 要： | 提出了一种简单的尺度和旋转不变性纹理分类方法．首先使用对数-极坐标变换对要分类的各纹理图像进行变换，生成对数-极坐标图像；然后以对数-极坐标图像的正则化以后的行投影数据向量构成纹理图像的特征向量；最后运用支持向量机实现尺度和旋转不变性纹理图像的分类．实验结果表明，该方法在尺度和旋转不变性纹理图像的分类中，准确率可达90％以上．
|
| 关 键 词： | 纹理分类 支持向量机 尺度不变性 旋转不变性 对数-极坐标变换 |
| 文章编号： | 1000-565X(2004)05-0026-04 |
Realization of the Texture Classification of Invariant Scale and Rotation by Support Vector Machines |
| |
| Jiang Jin-shan Yu Ying-lin. Realization of the Texture Classification of Invariant Scale and Rotation by Support Vector Machines[J]. Journal of South China University of Technology(Natural Science Edition), 2004, 32(5): 26-29,33 |
| |
| Authors: | Jiang Jin-shan Yu Ying-lin |
| |
| Abstract: | A simple and effective texture classification of invariant scale and rotation was proposed. In this classification, firstly, the texture images to be classified are translated into Log-polar images via Log-polar transformation. Then, the feature vectors of texture images are constituted with the normalized row project datum vector of the translated images. Finally, the support vector machines are used to the texture classification of invariant scale and rotation. Experimental results show that the proposed method is of an accuracy of more than 90% when it is used to the texture classification of invariant scale and rotation. |
| |
| Keywords: | texture classification support vector machine scale invariability rotation invariability Log-polar transformation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
