author = "Kubo, Diandra Akemi and Nazare, Tiago Santana de and Aguirre, 
                         Priscila Louise Ribeiro and Oliveira, Bruno Domingues and Duarte, 
                         Felipe Sim{\~o}es Lage Gomes",
          affiliation = "{Data Science Team - Itau Unibanco} and {Data Science Team - Itau 
                         Unibanco} and {Data Science Team - Itau Unibanco} and {Data 
                         Science Team - Itau Unibanco} and {Data Science Team - Itau 
                title = "The usage of U-Net for pre-processing document images",
            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 = "#deep-learning #computer-vision #image-processing.",
             abstract = "When processing documents in real-world scenarios, it is common to 
                         deal with artifacts that may hamper document analysis, such as 
                         stamps, noise and strange backgrounds. Aiming to mitigate these 
                         problems, we propose the use of U-Net, a very successful 
                         biomedical image segmentation network, for handwritten and machine 
                         text segmentation. In order to do so, we trained a model for each 
                         type of text. One of the main advantages presented is that the 
                         models are trained on artificial data, avoiding the wearisome task 
                         of data labeling. For the machine text segmentation model, we test 
                         its impacts on both word and character recognition when combined 
                         with the Tesseract OCR model. For the handwritten segmentation 
                         model, we present qualitative results. Initial experiments 
                         indicate that both models are able to improve results in their 
                         respective applications.",
  conference-location = "Foz do Igua{\c{c}}u, PR, Brazil",
      conference-year = "Oct. 29 - Nov. 1, 2018",
             language = "en",
                  ibi = "8JMKD3MGPAW/3S4ELD8",
                  url = "",
           targetfile = "sibgrapi_pi_cv.pdf",
        urlaccessdate = "2020, Nov. 29"