@InProceedings{MagalhãesQueiCabr:2018:ClTeUs,
               author = "Magalh{\~a}es, Whendell Feij{\'o} and Queiroz, Fabiane da Silva 
                         and Cabral, Raquel da Silva",
          affiliation = "{Universidade Federal de Alagoas - Campus Arapiraca} and 
                         {Universidade Federal de Alagoas - Centro de Ci{\^e}ncias 
                         Agr{\'a}rias} and {Universidade Federal de Alagoas - Campus 
                         Arapiraca}",
                title = "Classifica{\c{c}}{\~a}o de texturas usando a m{\'e}trica de 
                         centralidade closeness",
            booktitle = "Proceedings...",
                 year = "2018",
               editor = "Ross, Arun and Gastal, Eduardo S. L. and Jorge, Joaquim A. and 
                         Queiroz, Ricardo L. de and Minetto, Rodrigo and Sarkar, Sudeep and 
                         Papa, Jo{\~a}o Paulo and Oliveira, Manuel M. and Arbel{\'a}ez, 
                         Pablo and Mery, Domingo and Oliveira, Maria Cristina Ferreira de 
                         and Spina, Thiago Vallin and Mendes, Caroline Mazetto and Costa, 
                         Henrique S{\'e}rgio Gutierrez and Mejail, Marta Estela and Geus, 
                         Klaus de and Scheer, Sergio",
         organization = "Conference on Graphics, Patterns and Images, 31. (SIBGRAPI)",
            publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
              address = "Porto Alegre",
             keywords = "redes complexas, classifica{\c{c}}{\~a}o de texturas, 
                         centralidade closeness.",
             abstract = "In this paper, we propose a method for automatic description and 
                         classification of image texture. The images are modeled as 
                         weighted directed graphs. We use the centrality measure closeness 
                         and in-degree to generate a feature vector that describes the 
                         texture information. To validate the method, we train a k- Nearest 
                         Neighbors classifier and compare the obtained results with the 
                         Co-occurrence Matrix and Local Binary Patterns texture description 
                         techniques. For the experiments, we use the public dataset, 
                         KTH-TIPS. The accuracy of the proposed method is 95,52% that 
                         overcome the compared techniques.",
  conference-location = "Foz do Igua{\c{c}}u, PR, Brazil",
      conference-year = "29 Oct.-1 Nov. 2018",
             language = "pt",
                  ibi = "8JMKD3MGPAW/3S49SBP",
                  url = "http://urlib.net/ibi/8JMKD3MGPAW/3S49SBP",
           targetfile = "Classifica{\c{c}}{\~a}o de Texturas Usando a M{\'e}trica de 
                         Centralidade Closeness.pdf",
        urlaccessdate = "2024, Apr. 30"
}