author = "Rocha, Cleandro de Souza and Menezes, Mathias Afonso Guedes de and 
                         Oliveira, Felipe Gomes de",
          affiliation = "{Federal University of Amazoas} and {Federal University of 
                         Amazonas} and {Federal University of Amazonas}",
                title = "Detec{\c{c}}{\~a}o Autom{\'a}tica de Microcomponentes SMT 
                         Ausentes em Placas de Circuito Impresso",
            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 = "Vis{\~a}o de M{\'a}quina, Aprendizado de M{\'a}quina, 
                         Inspe{\c{c}}{\~a}o Industrial, Controle de Qualidade.",
             abstract = "This work presents a visual inspection approach to detect 
                         absence/presence of surface mount components (SMC) on printed 
                         circuit boards (PCB). We propose a methodology based on the 
                         combination of Machine Vision and Machine Learning to detect 
                         component absence, with more quality and precision, using noised 
                         digital images acquired directly from PCB industrial production 
                         line. The applicability of method was tested for automatic visual 
                         inspection in motherboards, where the demand of these components 
                         is high. The results obtained demonstrates the robustness of our 
                         methodology in images with high levels of gaussian and salt and 
                         pepper noise, obtaining 97.25% of hit rate.",
  conference-location = "S{\~a}o Jos{\'e} dos Campos",
      conference-year = "Oct. 4-7, 2016",
             language = "pt",
                  url = "",
           targetfile = "Sibgrapi2016_CameraReady.pdf",
        urlaccessdate = "2022, Jan. 19"