@InProceedings{MaiaJulcHira:2018:MaLeAp,
               author = "Maia, Ana Lucia Lima Marreiros and Julca-Aguilar, Frank Dennis and 
                         Hirata, Nina Sumiko Tomita",
          affiliation = "{University of S{\~a}o Paulo/State University of Feira de 
                         Santana} and {University of S{\~a}o Paulo} and {University of 
                         S{\~a}o Paulo}",
                title = "A Machine Learning approach for Graph-based Page Segmentation",
            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 = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "Page segmentation, document image, machine learning, graph, 
                         connected components classification, convolutional neural 
                         network.",
             abstract = "We propose a new approach for segmenting a document image into its 
                         page components (e.g. text, graphics and tables). Our approach 
                         consists of two main steps. In the first step, a set of scores 
                         corresponding to the output of a convolutional neural network, one 
                         for each of the possible page component categories, is assigned to 
                         each connected component in the document. The labeled connected 
                         components define a fuzzy over-segmentation of the page. In the 
                         second step, spatially close connected components that are likely 
                         to belong to a same page component are grouped together. This is 
                         done by building an attributed region adjacency graph of the 
                         connected components and modeling the problem as an edge removal 
                         problem. Edges are then kept or removed based on a pre-trained 
                         classifier. The resulting groups, defined by the connected 
                         subgraphs, correspond to the detected page components. We evaluate 
                         our method on the ICDAR2009 dataset. Results show that our method 
                         effectively segments pages, being able to detect the nine types of 
                         page components. Furthermore, as our approach is based on simple 
                         machine learning models and graph-based techniques, it should be 
                         easily adapted to the segmentation of a variety of document 
                         types.",
  conference-location = "Foz do Igua{\c{c}}u, PR, Brazil",
      conference-year = "29 Oct.-1 Nov. 2018",
                  doi = "10.1109/SIBGRAPI.2018.00061",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI.2018.00061",
             language = "en",
                  ibi = "8JMKD3MGPAW/3RP2P48",
                  url = "http://urlib.net/ibi/8JMKD3MGPAW/3RP2P48",
           targetfile = "Final_PaperID_50.pdf",
        urlaccessdate = "2024, Apr. 27"
}