Fault detection in wet blue goatskin using techniques of Computer Vision and Artificial Intelligence

• Carlos Estevão Bastos Sousa IFCE http://orcid.org/0000-0002-4272-0386
• Cláudio Marques de Sá Medeiros IFCE http://orcid.org/0000-0002-1663-8151
• Renato Francisco Pereira IFCE http://orcid.org/0000-0002-1939-2599
• Alcides Andrade Neto IFCE http://orcid.org/0000-0002-0522-3364

DOI: https://doi.org/10.5753/bresci.2020.11181

Abstract

Traditional tanneries acquire hides, in most cases, from small rural producers. Due to the rustic creation format, they are received with different types of defects. Such skins go through several processes until they are called wet blue. At this stage of production, qualification is carried out, which is based on the number of faults in the leather piece to define its level of quality. The nodetection of the failures can cause several financier losses to the sector. However, despite the difficulties encountered, the growth of this type of industry becomes clear. Thus, a methodology is proposed which presents an accuracy of 96.31% in the detection of flaws in leather parts wet blue.

Keywords: Tanneries, Fault detection, Qualification of leather

References

Amorim, W. P., Pistori, H., Pereira, M. C., and Jacinto, M. A. C. (2010). Attributes reduction applied to leather defects classification. 23rd SIBGRAPI Conference on Graphics, Patterns and Images, pages 353–359.

Annadurai, S. (2007). Fundamentals of Digital Image Processing. Always learning. Pearson.

Embrapa (2018). Novo censo agropecuário mostra crescimento de efetivo de caprinos e ovinos no nordeste. https://www.embrapa.br/cim-inteligencia-e-mercado-decaprinos-e-ovinos/busca-de-noticias/-/noticia/36365362/novo-censo-agropecuariomostra-crescimento-de-efetivo-de-caprinos-e-ovinos-no-nordeste. Acesso em 28 dez. 2019.

Gutterres, M. (2003). Desenvolvimento Sustentável em Curtumes. XVI Encontro Nacional da ABQTIC, Porto Alegre - RS.

Haralick, R. M., Shanmugam, K., and Dinstein, I. (1973). Textural features for image classification. IEEE TRANSATIONS ON SYSTEMS, MAN AND CYBERNETICS, SMC-3(6):610–621.

Huang, D., Shan, C., Ardabilian, M., Wang, Y., and Chen, L. (2011). Local binary patterns and its application to facial image analysis: A survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 41(6):765–781.

Mohanaiah, P., Sathyanarayana, P., and GuruKumar, L. (2013). Image texture feature extraction using glcm approach. International Journal of Scientific and Research Publications., 3:1–5.

Ojala, T., Pietikäinen, M., and Mäenpää, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell., 24(7):971–987.

Pereira, R., Medeiros, C., and Filho, P. P. (2018). Goat leather quality classification using computer vision and machine learning. International Joint Conference on Neural Networks - IJCNN, pages 01–08.

Renato Pereira, F. (2018). Qualificação de amostras de couro caprino utilizando visão computacional e inteligência computacional. Master’s thesis, Instituto Federal de Educação, Ciência e Tecnologia do Ceará (IFCE), Fortaleza, CE, Brazil.

Santos Filho, E. (2013). Um sistema de visão computacional para classificação de couro caprino. Master’s thesis, Universidade Federal do Ceará (UFC), Fortaleza, CE, Brazil.

Schwartz, W. R. and Pedrini, H. (2003). Método para classificação de imagens baseada em matrizes de co-ocorrência utilizando características de textura. III Colóquio Brasileiro de Ciências Geodésicas.