@InProceedings{LouzadaPaul:2021:ClMoIm,
               author = "Louzada, Henrique Almeida and Paula, Maria In{\^e}s Lage de",
          affiliation = "{Pontifical Catholic University of Minas Gerais} and {Pontifical 
                         Catholic University of Minas Gerais}",
                title = "Classificando Modelos de Implantes Dent{\'a}rios Usando Redes 
                         Neurais Convolucionais com Dados Sintetizados",
            booktitle = "Proceedings...",
                 year = "2021",
               editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and 
                         Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario 
                         and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos, 
                         Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira, 
                         Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir 
                         A. and Fernandes, Leandro A. F. and Avila, Sandra",
         organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
            publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
              address = "Porto Alegre",
             keywords = "dental implant, classification, computer vision, convolutional 
                         neural networks.",
             abstract = "Classifying dental implants in radiography images using 
                         Convolutional Neural Networks implies training them using images 
                         that are hardly publicly available. This work seeks to build a 
                         synthetic database of dental implants and test its effectiveness 
                         when using it to train one of these networks. Three different 
                         implant models were methodically photographed and basic Data 
                         Augmentation and Style Transfer techniques were used to create a 
                         training database. Some real X-ray images were collected to 
                         compose a test dataset and a simple Convolutional Neural Network 
                         was architected. Training this network with the synthetic set and 
                         testing it with the real set resulted in a predictive model with 
                         71% overall accuracy, which highlights the possibility of using a 
                         synthetic database for this purpose. Implications for results and 
                         future work were discussed.",
  conference-location = "Gramado, RS, Brazil (virtual)",
      conference-year = "18-22 Oct. 2021",
             language = "pt",
                  ibi = "8JMKD3MGPEW34M/45EA6NB",
                  url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45EA6NB",
           targetfile = "
                         
                         Classifying_Dental_Implant_Models_Using_Convolutional_Neural_Networks_on_Synthetized_Datasets.pdf",
        urlaccessdate = "2024, May 06"
}