An Invariant Multiscale Texture Image Analysis Algorithm Based on Radon Transform
基于Radon变换的纹理图像多尺度不变量分析算法

For image texture analysis,an invariant texture recognition algorithm is proposed based on Radon transform.Firstly,Radon transform is used to project the image to 1-D space,and then the projection data is transformed via a translation and scaling invariant adaptive 1-D wavelet transform,thus the feature matrix with translation and scaling invariance is derived.Multiscale analysis is employed for the feature matrix,and the energy values at different scales are proven not only to be invariant under image translation,scaling and rotation,but also to reflect the different energy distribution of the texture image at different scales.After the feature vector is availabe,support vector machine(SVM) is used for classification.Comparing with other methods simulations are given to obtain insight into the effectiveness of our method.