Close
Metadata

%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2017/09.08.01.03
%2 sid.inpe.br/sibgrapi/2017/09.08.01.03.07
%T Classification of Failures in Goat Leather Samples Using Computer Vision and Machine Learning
%D 2017
%8 Oct. 17-20, 2017
%A Pereira, Renato F.,
%A Dias, Madson Luis D.,
%A Medeiros, Claudio Marques de Sá,
%A Rebouças Filho, Pedro Pedrosa,
%@affiliation Programa de Pós-Graduação em Ciência da Computação do Instituto Federal de Educação, Ciência e Tecnologia do Ceará
%@affiliation Programa de Pós-Graduação em Ciência da Computação do Instituto Federal de Educação, Ciência e Tecnologia do Ceará
%@affiliation Programa de Pós-Graduação em Ciência da Computação do Instituto Federal de Educação, Ciência e Tecnologia do Ceará
%@affiliation Programa de Pós-Graduação em Ciência da Computação do Instituto Federal de Educação, Ciência e Tecnologia do Ceará
%E Torchelsen, Rafael Piccin,
%E Nascimento, Erickson Rangel do,
%E Panozzo, Daniele,
%E Liu, Zicheng,
%E Farias, Mylène,
%E Viera, Thales,
%E Sacht, Leonardo,
%E Ferreira, Nivan,
%E Comba, João Luiz Dihl,
%E Hirata, Nina,
%E Schiavon Porto, Marcelo,
%E Vital, Creto,
%E Pagot, Christian Azambuja,
%E Petronetto, Fabiano,
%E Clua, Esteban,
%E Cardeal, Flávio,
%B Conference on Graphics, Patterns and Images, 30 (SIBGRAPI)
%C Niterói, RJ
%S Proceedings
%I Sociedade Brasileira de Computação
%J Porto Alegre
%K Goat Leather, Classification of Failures, Computer Vision, Machine Learning.
%X Textile industry has used goat skins in manufactur- ing products that require high quality control. Thus, a specialist performed a skins qualities classification to put a price on the goat leather sample, but this evaluation depends on whom evaluate. To reduce these divergences and to increase the productivity on the textile industry area, this paper presents a new approach to detect leather failure using feature extractor and machine learning classifiers. Also, a new feature extractor, called of Pixel Intensity Analyzer (PIA), is proposed for this application. Experiments were performed with a real data set comparing PIA with two other features extractors using machine learning classifiers with each one. In accuracy, the best approach was LBP with LS-SVM (RBF), but in processing time as a very important factor, since it is a real-time application to the industry, the PIA combined with ELM presents the best cost-effective because it also has excellent accuracy rates.
%@language en
%3 manuscript_Sibgrapi.pdf


Close