Texture analysis using complex system models: fractal dimension, swarm systems and non-linear diffusion
Resumo
Texture is one of the primary visual features used to computationally describe the patterns found in nature. Existing computational methods, however, do not successfully discriminate the complexity of texture patterns. Such methods disregard the possibility of describing images by benefiting from the complex systems properties that are characteristic to textures. To do so, we created approaches based on the Bouligand-Minkowski fractal dimension, swarm-system Artificial Crawlers, and non-linear diffusion of Perona-Malik, techniques that led to methodologies with efficacy and efficiency comparable to the state-ofthe-art. The results achieved in the four methodologies described in this work demonstrated the validity and the potential of our hypothesis in tasks of pattern recognition. The contributions of our methodologies shall support advances in materials engineering, computer vision, and agriculture.
