A New Approach for Wet Blue Leather Defect Segmentation

  • Patricio Villar
  • Marco Mora
  • Paulo Gonzalez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7042)

Abstract

In the process plants where beef skin is processed, leather classification is done manually. An expert visually inspects the leather sheet and classifies them based on the different types of defects found on the surface, among other factors. In this study, an automatic method for defect classification of the Wet Blue leather is proposed. A considerable number of descriptors are computerized from the Gray Scale image and the RGB and HSV color model. Features were chosen based on the Sequential Forward Selection method, which allows a high reduction of the numbers of descriptors. Finally, the classification is implemented by using a Supervised Neural Network. The problem formulation is adequate, allowing a high rate of success, obtaining a method with wide range of possibilities for implementation.

Keywords

Local Binary Pattern Gray Scale Image Sequential Forward Selection Leather Processing Supervise Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Yeh, C., Perng, D.: Establishing a Demerit Count Reference Standard for the Classification and Grading of Leather Hides. International Journal of Advanced Manufacturing 22, 731–738 (2001)CrossRefGoogle Scholar
  2. 2.
    Kwak, C., Ventura, J., Tofang-Sazi, K.: Automated Defect Inspection and Classification of Leather Fabric. Intelligent Data Analysis 5, 355–370 (2001)Google Scholar
  3. 3.
    Georgieva, L., Krastev, K., Angelov, N.: Identification of Surface Leather Defects. In: Proceedings of the 4th International Conference on Computer Systems and Technologies, pp. 303–307 (2003)Google Scholar
  4. 4.
    Amorim, W., Viana, R., Rodrigues, R., Pistori, H.: Desenvolvimento de um Software de Processamento e Geracao de Imagens para Classificacao de Couro Bovino. In: Workshop de Iniciação Científica - SIBGRAPI 2006 (2006)Google Scholar
  5. 5.
    Pistori, H., Paraguassu, W., Martins, P., Conti, M., Pereira, M., Jacinto, M.: Defect Detection in Raw Hide and Wet Blue Leather. In: Proceedings of the International Symposium on Computational Modelling of Objects Represented in Images 2006, CompIMAGE 2006 (2006)Google Scholar
  6. 6.
    Viana, R., Rodrigues, R.B., Alvarez, M.A., Pistori, H.: SVM with Stochastic Parameter Selection for Bovine Leather Defect Classification. In: Mery, D., Rueda, L. (eds.) PSIVT 2007. LNCS, vol. 4872, pp. 600–612. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  7. 7.
    Nara, L., Pistori, H.: Selecao de Atributos para a Segmentacao do Couro Bovino. In: Anais do IV Workshop de Visao Computational (2008)Google Scholar
  8. 8.
    Nara, L., Pistori, H.: A Comparative Analysis of Attribute Reduction Algorithms Applied to Wet-Blue Leather Defects Classification. In: Proceedings of the XXII Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2009 (2009)Google Scholar
  9. 9.
    Mery, D., Soto, A.: Features: The more the better. In: Proceedings of the 8th Conference on Signal Processing, Computational Geometry and Artificial Vision (ISCGAV 2008), pp. 46–51 (2008)Google Scholar
  10. 10.
    Jain, A., Robert, P., Duin, M.J.: Statistical Pattern Recognition: A Review. Intelligent Data Analysis 22, 4–34 (1999)Google Scholar
  11. 11.
    Funahashi, K.: On the Approximate Realization of Continuous Mappings by Neural Networks. Neural Networks 2, 183–192 (1989)CrossRefGoogle Scholar
  12. 12.
    Forensee, F., Hagan, M.: Gauss-Newton Approximation to Bayesian Learning. In: Proceedings of the International Joint Conference on Neuronal Networks, vol. 3, pp. 1930–1935 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Patricio Villar
    • 1
  • Marco Mora
    • 1
  • Paulo Gonzalez
    • 1
  1. 1.Les Fous du Pixel Image Processing Research Group Department of Computer ScienceCatholic University of MauleTalcaChile

Personalised recommendations