AgradecimentosAo meu orientador Prof. Dr. João Batista Neto, suas orientações e amizade foram de vital importância para o sucesso do meu mestrado.Ao professor Francisco Rodrigues, seus aportes foram muito importantes para nosso trabalho.Aos meus pais Oscar e Ruth, seu amor, apoio e fê em mim, são o pilar da minha vida. À minha irmã Alejandra por ser a luz da nossa família, principalmente, na minha ausência. À Aurea Soriano Vargas, minha noiva, o maior presente de Deus. À Glenda Botelho, nossa amizade e as inúmeras horas de trabalho em equipe, foram a fórmula do sucesso deste mestrado . À CPNq, pelo apoio financeiro.iii v Tanta coisa por fazer e cada um tem sua própria tarefa na façanha de nosso tempo. Santíssima Mãe, interceda para que eu receba força e o encorajamento para cooperar com a grande tarefa de mudar nosso mundo colocando meu grão de areia, que poderia muito bem fazer a diferença. Amém. Palavras-chave: Segmentação de Imagens, Redes Complexas, Super Pixels, Detecção de Comunidades.vii Abstract Image segmentation is still a challenging stage of the pattern recognition process. Amongst the various segmentation approaches, some are based on graph partitioning, many of which show some drawbacks, such as the high processing times. Recent trends on complex network theory have contributed considerably to the development of graph-based pattern recognition techniques. The identification of group of vertices can be considered a community detection process according to complex network theory. Since data clustering is closely related to image segmentation, image segmentation tasks can also be tackled by complex networks. However, complex network-based image segmentation poses a very important limitation: the excessive number of nodes of the underlying network. In this work we propose a approach based on complex networks suitable for the segmentation of image with large dimensions that is accurate and yet fast. To accomplish that, we have incorporated the concept of Super Pixels aiming at reducing the number of the nodes in the network. The results have shown that the proposed approach delivered accurate image segmentation within low computational times. Another contribution worth mentioning is the determination of the best values for the parameters needed by the underlying graphbased segmentation and community detection algorithms, which enabled the proposed approach to become less dependent on the parameters. To the best of our knowledge, this is a new contribution to the field.