On the Fuzzy Texture Spectrum for Natural Microtextures Characterization.

Abstract Texture is an important spatial feature, useful for segmenting objects in an image. Texture Spectrum is a statistical approach to texture analysis. In this paper we proposed a Texture-based approach that considers the vagueness of the images and has into account the human beings. Keywords: Texture analysis, Texture Spectrum, Fuzzy sets. 1 Introduction Texture segmentation has long been an important topic in image processing. Basically, it aims at segmenting a textured image into several regions with the same texture features. An effective and efficient texture segmentation method will be very useful in applications like the analysis of aerial images, biomedical images and seismic images as well as the automation of industrial applications. In the field of image segmentation, an automatic texture classification process is necessary. The information from texture can be added to other characteristics such as color or brightness in order to achieve a more robust segmentation. A number of methods for the description of the texture have been proposed in the literature ([1], [4]-[6]). A common aspect in most of them is the construction of an intermediate formulation, suitable for the description of the distribution of neighbouring pixels in the image. Other methods aim to the transformation of the original image in another one, using filtering procedures in order to indicate special texture characteristics of the image. Texture spectrum has been introduced in the last few years ([2], [3]), and was initially used as a texture filtering approach. The key concept of this method is the computation of the relative intensity relations between the pixels in a small neighbourhood and not on their absolute intensity values. The importance of the texture spectrum method is determined by the extraction of local texture information for each pixel and of the characterization of textural aspect of a digital image in the form of a spectrum. The application of the texture spectrum methodology to a given digital image results into the texture spectrum, which characterizes the original image maintaining the image’s texture characteristics. In present work we propose an approach based on the texture spectrum method, which considers the vagueness within the data for getting a robust microtexture characterization method. The paper is organized as follows: first, the texture spectrum technique will be briefly presented. The power of this technique and his limitations will be discussed. Secondly, the classification will be improved by means of using fuzzy numbers. Thirdly, a concrete example will illustrate the article, giving some real results. Finally, a conclusion will reveal the power of the spectrum method used together with the fuzzy theory.