CLASSIFYING TEXTURE IMAGES USING ARTIFICIAL AGENTS, FRACTAL DIMENSION AND EXTREME LEARNING MACHINES

This work proposes a new method of representing textures on digital images through their maximum (or minimum if the negative of the image is used) and dierent intensity borders by means of artificial beings called articial hikers that search for the maximum of a texture image and in doing so, represent the diferent characteristics of the image. The technique has two main parameters that can be adjusted in order to emphasize the greatest maximum of an image and diferent frequency borders. For the classication of  textures, the technique of articial hikers was combined with fractal dimension analysis and extreme learning machine and it presented superior results compared to previous works dealing with texture classication with artificial agents.