RESUMEN
To quantify the concept of similarity between classes of images three measures and algorithms of calculation are proposed. The first measure is calculated through the frequency of misclassification of subimages sampled randomly from images. The second one is calculated through the cross membership of the mass center of a class in a feature space. The third measure is defined through the membership of subimages, using the distance between each subimage and the mass center of a class in a feature space. We study these measures, classifying images in the coordinated clusters representation (CCR) feature space with the minimum distance classifier. A database of images of Rosa Porriño granite tiles, previously classified by three human experts, is used in the experiments. The calculated similarity between classes is in excellent accordance with the qualitative evaluation by the human experts.
RESUMEN
The efficiency of texture image classification is certainly influenced by image scale when a feature space or a classification method is not scale invariant. An alternative approach to the scale-invariant techniques is proposed that first estimates an effective image scale and then uses it to adjust texture features to get the best possible texture image recognition and classification. We use the correlation distance between pixels as a measure of the scale of texture images. We study the performance of classification of texture images in the coordinated cluster representation (CCR) versus an image scale and the size of the scanning window used for the coordinated cluster transform. Given the number of classes to be classified in, we find that an optimal (up to 100%) classification efficiency in the CCR feature space is obtained by changing an image scale and/or the size of the scanning window in the coordinated cluster transform.