@InProceedings{CíceroOlivBote:2016:DeLeCo,
               author = "C{\'{\i}}cero, Felipe Moure and Oliveira, Ary Henrique and 
                         Botelho, Glenda",
          affiliation = "{Universidade Federal do Tocantins} and {Universidade Federal do 
                         Tocantins} and {Universidade Federal do Tocantins}",
                title = "Deep Learning and Convolutional Neural Networks in the Aid of the 
                         Classification of Melanoma",
            booktitle = "Proceedings...",
                 year = "2016",
               editor = "Aliaga, Daniel G. and Davis, Larry S. and Farias, Ricardo C. and 
                         Fernandes, Leandro A. F. and Gibson, Stuart J. and Giraldi, Gilson 
                         A. and Gois, Jo{\~a}o Paulo and Maciel, Anderson and Menotti, 
                         David and Miranda, Paulo A. V. and Musse, Soraia and Namikawa, 
                         Laercio and Pamplona, Mauricio and Papa, Jo{\~a}o Paulo and 
                         Santos, Jefersson dos and Schwartz, William Robson and Thomaz, 
                         Carlos E.",
         organization = "Conference on Graphics, Patterns and Images, 29. (SIBGRAPI)",
            publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
              address = "Porto Alegre",
             keywords = "deep learning, convolutional neural networks, melanoma 
                         classification.",
             abstract = "Pattern recognition in digital images is a major limitation in 
                         machine learning area. But, in recent years, deep learning has 
                         rapidly been diffused, providing large advancements in visual 
                         computing by solving the main problems that machine learning 
                         imposes. Based on these advances, this study aims to improve 
                         results of a problem well-known by visual computing, the 
                         classification of melanoma, this one is classified as a malignant 
                         tumor, highly invasive and easily confused with other skin 
                         diseases. To achieve this, we use some techniques of deep learning 
                         to try to get better results in the task of classifying whether a 
                         melanotic lesion is the malignant type (melanoma) or not (nevus). 
                         In this work we present a training approach using a custom dataset 
                         of skin diseases, transfer learning, convolutional neural networks 
                         and data augmentation of the deep network ResNet (Deep Residual 
                         Network).",
  conference-location = "S{\~a}o Jos{\'e} dos Campos, SP, Brazil",
      conference-year = "4-7 Oct. 2016",
             language = "en",
                  ibi = "8JMKD3MGPAW/3MC992S",
                  url = "http://urlib.net/ibi/8JMKD3MGPAW/3MC992S",
           targetfile = "16.pdf",
        urlaccessdate = "2024, Apr. 29"
}