Multiresolution eigenimages for texture classification

Following an idea from B.M. ter Haar Romeny (see "Front-end vision and multiscale image analysis", Kluwer Academic Publishers, 2002), based on the Gaussian properties of eigenimages, the paper presents a new technique for texture classification using multiresolution eigenimages. The input image, composed of two textures from the Brodatz album, is subdivided into N sub-images of fixed size δ×δ, which are blurred with a Gaussian and normalized. The application of a Hotelling transform decomposes each sub-image into δ² eigenimages. The R largest resulting coefficients can be used for classification of the texture present in the sub-images. Classification is done using the fuzzy C-means (FCM) algorithm and the performance is measured with an appropriate quality factor. We discuss the successful application of this technique, as well as the influence of the different parameters of the classification process on several pairs of textures. Moreover, the combing of Hotelling coefficients obtained with different values of δ is shown to improve the performance, based on the idea of analyzing the texture at different levels of resolution.