SVM with Stochastic Parameter Selection for Bovine Leather Defect Classification

  • Roberto Viana
  • Ricardo B. Rodrigues
  • Marco A. Alvarez
  • Hemerson Pistori
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4872)


The performance of Support Vector Machines, as many other machine learning algorithms, is very sensitive to parameter tuning, mainly in real world problems. In this paper, two well known and widely used SVM implementations, Weka SMO and LIBSVM, were compared using Simulated Annealing as a parameter tuner. This approach increased significantly the classification accuracy over the Weka SMO and LIBSVM standard configuration. The paper also presents an empirical evaluation of SVM against AdaBoost and MLP, for solving the leather defect classification problem. The results obtained are very promising in successfully discriminating leather defects, with the highest overall accuracy, of 99.59%, being achieved by LIBSVM tuned with Simulated Annealing.


Support Vector Machines Pattern Recognition Parameter Tuning 


  1. 1.
    Matthey, H., Fabiosa, J.F., Fuller, F.H.: Brazil: The future of modern agriculture. MATRIC  (2004)Google Scholar
  2. 2.
    da Costa, A.B.: Estudo da competitividade de cadeias integradas no brasil: Impactos das zonas de livre comercio. Technical report, Instituto de Economia da Universidade Estadual de Campinas (2002)Google Scholar
  3. 3.
    Yeh, C., Perng, D.B.: Establishing a demerit count reference standard for the classification and grading of leather hides. International Journal of Advanced Manufacturing 18, 731–738 (2001)CrossRefGoogle Scholar
  4. 4.
    Sobral, J.L.: Optimised filters for texture defect detection. In: Proc. of the IEEE International Conference on Image Processing, September 2005, vol. 3, pp. 565–573. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  5. 5.
    Kumar, A., Pang, G.: Defect detection in textured materials using gabor filters. IEEE Transactions on Industry Applications 38(2) (2002)Google Scholar
  6. 6.
    Georgieva, L., Krastev, K., Angelov, N.: Identification of surface leather defects. In: CompSysTech 2003: Proceedings of the 4th international conference on Computer systems and technologies, pp. 303–307. ACM Press, New York (2003)Google Scholar
  7. 7.
    Krastev, K., Georgieva, L., Angelov, N.: Leather features selection for defects’ recognition using fuzzy logic. In: CompSysTech 2004: Proceedings of the 5th international conference on Computer systems and technologies, pp. 1–6. ACM Press, New York (2004)Google Scholar
  8. 8.
    Branca, A., Tafuri, M., Attolico, G., Distante, A.: Automated system for detection and classification of leather defects. NDT and E International 30(1), 321–321 (1997)Google Scholar
  9. 9.
    Pistori, H., Paraguassu, W.A., Martins, P.S., Conti, M.P., Pereira, M.A., Jacinto, M.A.: Defect detection in raw hide and wet blue leather. In: CompImage (2006)Google Scholar
  10. 10.
    Osuna, E., Freund, R., Girosi, F.: Training support vector machines: an application to face detection. In: CVPR 1997, Puerto Rico, pp. 130–136 (1997)Google Scholar
  11. 11.
    Chetverikov, D.: Texture analysis using feature-based pairwise interaction maps. Pattern Recognition 32(3), 487–502 (1999)CrossRefGoogle Scholar
  12. 12.
    Hseu, H.W.R., Bhalerao, A., Wilson, R.G.: Image matching based on the co-occurrence matrix. Technical Report CS-RR-358, Coventry, UK (1999)Google Scholar
  13. 13.
    Platt, J.: Sequential minimal optimization: A fast algorithm for training support vector machines (1998)Google Scholar
  14. 14.
    Freund, Y., Schapire, R.E.: A short introduction to boosting. Journal of Japanese Society for Artificial Intelligence 14(5), 771–780 (1999)Google Scholar
  15. 15.
    Jacinto, M.A.C., Pereira, M.A.: Industria do couro: programa de qualidade e estratificacao de mercado com base em caracteristicas do couro. Simposio de producao de gado de corte, 75–92 (2004)Google Scholar
  16. 16.
    Gomes, A.: Aspectos da cadeia produtiva do couro bovino no Brasil e em Mato Grosso do Sul. In: Palestras e proposicoes: Reunioes Tecnicas sobre Couros e Peles, 25 a 27 de setembro e 29 de outubro a 1 de novembro de 2001, pp. 61–72. Embrapa Gado de Corte (2002)Google Scholar
  17. 17.
    Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing. Science, Number 4598 220(4598), 671–680 (1983)MathSciNetGoogle Scholar
  18. 18.
    Imbault, F., Lebart, K.: A stochastic optimization approach for parameter tuning of support vector machines. In: Proceedings of the Pattern Recognition, 17th International Conference on (ICPR 2004), pp. 597–600. IEEE Computer Society Press, Los Alamitos (2004)CrossRefGoogle Scholar
  19. 19.
    Boardman, M., Trappenberg, T.: A heuristic for free parameter optimization with support vector machines. In: Proceedings of the 2006 IEEE International Joint Conference on Neural Networks, pp. 1337–1344. IEEE Computer Society Press, Los Alamitos (2006)Google Scholar
  20. 20.
    Mitchell, T.M.: The discipline of machine learning. Technical Report CMU-ML-06-108 (2006)Google Scholar
  21. 21.
    Vapnik, V.N.: An overview of statistical learning theory. IEEE Transactions on Neural Networks 10(5), 988–999 (1999)CrossRefGoogle Scholar
  22. 22.
    Hsu, C.W., Lin, C.J.: A comparison of methods for multi-class support vector machines. IEEE Transactions on Neural Networks 13, 415–425 (2002)CrossRefGoogle Scholar
  23. 23.
    Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques. Machine Learning 36(1-2), 105–139 (2005)Google Scholar
  24. 24.
    Amorim, W.P., Viana, R.R.R.P.H.: Desenvolvimento de um software de processamento e geracao de imagens para classificacao de couro bovino. SIBGRAPI- Workshop of Undergraduate Works (2006)Google Scholar
  25. 25.
    Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques, 2nd edn. Morgan Kaufmann, San Francisco (2005)zbMATHGoogle Scholar
  26. 26.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines, Software (2001), available at:

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Roberto Viana
    • 1
  • Ricardo B. Rodrigues
    • 1
  • Marco A. Alvarez
    • 2
  • Hemerson Pistori
    • 1
  1. 1.GPEC - Dom Bosco Catholic University, Av. Tamandare, 6000 Campo GrandeBrazil
  2. 2.Department of Computer Science, Utah State University, Logan, UT 84322-4205USA

Personalised recommendations