%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2017/08.29.01.15
%2 sid.inpe.br/sibgrapi/2017/08.29.01.15.25
%T Quality Control System for Ceramic Tiles using Segmentation-based Fractal Texture Analysis and SVM
%D 2017
%A Macarini, Luiz Antonio,
%A Weber, Tiago Oliveira,
%@affiliation Universidade Federal de Santa Catarina
%@affiliation Universidade Federal de Santa Catarina
%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, Brazil
%8 17-20 Oct. 2017
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K Image Processing, Machine Learning, SFTA, Ceramic Tiles, Defect Detection.
%X The ceramic industry has a highly automated production system. The quality control, however, is still performed by humans, which limits its speed and precision. This work proposes a complete verification system for ceramic tiles based on image processing and machine learning. The system has four steps: image acquisition, pre-processing, feature extraction and classification. The feature extraction step uses Segmentation-based Fractal Texture Analysis (SFTA). A Support Vector Machine is employed to classify the ceramic tiles. The system is implemented using OpenCV libraries. In total, 783 ceramic tiles were used, being 80% for training and 20% to testing. The present work had reached the proposed objectives, both in processing time and accuracy, achieving 98.68% of detection rate.
%@language en
%3 SIBGRAPI_Luiz_Tiago.pdf