【摘要】 提出了一种应用Radon变换和离散平稳小波变换(SWT)的旋转不变纹理分类算法。该方法首先对纹理图像进行Radon变换将旋转转化为平移,再用具有平移不变性的离散平稳小波对变换后的图像滤波并计算各子带的能量值组成旋转不变特征向量,最后利用支持向量机实现纹理图像的分类。将本方法与其它旋转不变纹理分类法进行比较,实验结果表明,提出的方法能有效地提高正确分类率。更多还原

【Abstract】 A rotation invariant texture classification method using Radon transform and discrete stationary wavelet transform(SWT) is proposed. First, the texture image is translated by Radon transform to convert the rotation to translation, the rotation invariant feature vector is composed of the energies of the subbands acquired by SWT which is shift invariant to the translated texture image, the support vector machines(SVM) is used to the texture classification at last. This method is compared with other rotation invariant texture classification method, the experiment results show that it can improve the classification rate effectively.更多还原