A simplified gravitational model to analyze texture roughness

Textures are among the most important visual attributes in image analysis. This paper presents a novel method to analyze texture, based on representing states of a simplified gravitational collapse from an image and extracting information from each state using fractal dimension. In this approach, an image evolves in times t = { 1 , 2 , … , 20 } , each time representing a state, which is explored by the Bouligand–Minkowski method using radius r = { 3 , 4 , … , 8 } . These parameters allow to create a set of feature vectors, which were extracted from Brodatzʹs textures and leaf textures. The best classification results were 98.75% and 86.67% of success rate (percentage of samples correctly classified) for these two databases, respectively. These results prove that the proposed approach opens a promising source of research in texture analysis to be explored.