Journal of Intelligent Manufacturing

, Volume 30, Issue 1, pp 351–361 | Cite as

Online inspection system based on machine learning techniques: real case study of fabric textures classification for the automotive industry

  • Pedro Malaca
  • Luis F. RochaEmail author
  • D. Gomes
  • João Silva
  • Germano Veiga


This paper focus on the classification, in real-time and under uncontrolled lighting, of fabric textures for the automotive industry. Many industrial processes have spatial constraints that limit the effective control of illumination of their vision based systems, hindering their effectiveness. The ability to overcome these problems using robust classification methods with suitable pre-processing techniques and choice of characteristics will increase the efficiency of this type of solutions with obvious production gains and thus economical. For this purpose, this paper studied and analyzed various pre-processing techniques, and selected the most appropriate fabric characteristics for the considered industrial case scenario. The methodology followed was based on the comparison of two different machine learning classifiers, ANN and SVM, using a large set of samples with a large variability of lightning conditions to faithfully simulate the industrial environment. The obtained solution shows the sensibility of ANN over SVM considering the number of features and the size of the training set, showing the better effectiveness and robustness of the last. The characteristics vector uses histogram equalization, Laws filter and Sobel filter, and multi-scale analysis. By using a correlation based method was possible to reduce the number of features used, achieving a better balanced between processing time and classification ratio.


Computer vision Perception and recognition Fabric analyses Machine learning Uncontrolled illumination Automotive industry 


  1. AForge.NET: Computer Vision, Artificial Intelligence, Robotics [Internet]. [cited January 7, 2014]. Available from
  2. Ahmed, S. A., Dey, S., & Sarma, K. K. (2011). Image texture classification using artificial neural network (ANN). In 2011 2nd national conference on emerging trends and applications in computer science (NCETACS) (p. 14).Google Scholar
  3. Aksoy, M. S., Torkul, O., & Cedimoglu, I. H. A. (2004). An industrial visual inspection system that uses inductive learning. Journal of Intelligent Manufacturing, 15, 569–574.CrossRefGoogle Scholar
  4. Aleksander, I., & Morton, H. (1990). An introduction to neural computing (Vol. 3). London: Chapman and Hall.Google Scholar
  5. Arun, D. K. (1993). Artificial neural networks for image understanding (1st ed.). New York, NY: Wiley.Google Scholar
  6. Ballard, D. H., & Brown, C. M. (1982). Computer vision. London: Prentice-Hall.Google Scholar
  7. Ben Salem, Y., & Nasri, S. (2010). Automatic recognition of woven fabrics based on texture and using SVM (pp. 429–434). Image and Video Processing: Journal Signal.Google Scholar
  8. Brosnan, T., & Sun, D.-W. (2004). Improving quality inspection of food products by computer visiona review. Journal of Food Engineering, 61(1), 3–16.CrossRefGoogle Scholar
  9. Burges, C. J. C. (1998). A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2, 121–167. doi: 10.1023/A:1009715923555.CrossRefGoogle Scholar
  10. Burt, P. J., & Adelson, E. H. (1983). The Laplacian pyramid as a compact image code. IEEE Transactions on Communications, 31(4), 53240.CrossRefGoogle Scholar
  11. Fellows, P. J. (2009). In P. J. Fellows (Eds.), Woodhead publishing series in food science, technology and nutrition (3rd edn, pp. 1–8). Woodhead Publishing, Food Processing Technology. ISBN 9781845692162. doi: 10.1533/9781845696344.1.
  12. Ghorai, S., Mukherjee, A., Gangadaran, M., & Dutta, P. K. (2013). Automatic defect detection on hot-rolled flat steel products. IEEE Transactions on Instrumentation and Measurement, 62(3), 612–621.CrossRefGoogle Scholar
  13. Gonzalez, R. C., & Woods, R. E. (2006). Digital image processing. Upper Saddle River, NJ: Prentice-Hall.Google Scholar
  14. Haralick, R. M., Shanmugam, K., & Dinstein (1973). Its’Hak, “Textural features for image classification”. IEEE Transactions on Systems, Man and Cybernetics, SMC-3(6), 610–621.Google Scholar
  15. Hosseini, S., Al Khaled, A., & Vadlamani, S. (2014). Hybrid imperialist competitive algorithm, variable neighborhood search, and simulated annealing for dynamic facility layout problem. Neural Computing and Applications, 25(7–8), 1871–1885.CrossRefGoogle Scholar
  16. Jeon, B. S., Bae, J. H., & Suh, M. W. (2013). Automatic recognition of woven fabric patterns by an artificial neural network. Textile Research Journal, 73(7), 645–650. doi: 10.1177/004051750307300714.CrossRefGoogle Scholar
  17. Kotsiantis, S. B. (2007). Supervised machine learning: A review of classification techniques. In Maglogiannis, I., Karpouzis, K., Wallace, M., & Soldatos, J. (Eds.), Proceedings of the 2007 conference on emerging artificial intelligence applications in computer engineering: Real word AI systems with applications in eHealth, HCI, information retrieval and pervasive technologies (pp. 3–24). Amsterdam, The Netherlands: I.O.S. Press.Google Scholar
  18. Kwak, C., Ventura, J. A., & Tofang-Sazi, K. (2000). A neural network approach for defect identification and classification on leather fabric. Journal of Intelligent Manufacturing, 11, 485–499.CrossRefGoogle Scholar
  19. Laws, K. I. (2014). Textured image segmentation. Ph.D. Thesis, University of Southern California Los Angels Image Processing Institute [cited January 4, 2014]. Available from
  20. Li, S., Kwok, J. T., Zhu, H., & Wang, Y. (2003). Texture classification using the support vector machines. Pattern Recognition, 36(12), 288393.CrossRefGoogle Scholar
  21. Loke, K.S. (2009). An approach to textile recognition, pattern recognition. In P.-Y. Yan (Ed.), ISBN: 978-953-307-014-8, InTech, doi: 10.5772/7531. Available from
  22. MVTec HALCON 10—Highlights of version 10 [Internet]. [cited January 7, 2014]. Available from
  23. Ojala, T., Pietikinen, M., & Nisula, J. (1996). Determining composition of grain mixtures by texture classification based on feature distributions. International Journal of Pattern Recognition and Artificial Intelligence, 10, 7382.CrossRefGoogle Scholar
  24. Palm, C. (2004). Color texture classification by integrative co-occurrence matrices. Pattern Recognition, 37(5), 965–976.CrossRefGoogle Scholar
  25. Pavelka, A. P., & Procházka, P. (2004). Algorithms for initialization of neural network weights. Tech Comput: Proc. Conf.Google Scholar
  26. Pinto, N., Cox, D. D., & DiCarlo, J. J. (2008). Why is real-world visual object recognition hard? PLoS Comput Biol, 4(1), e27. doi: 10.1371/journal.pcbi.0040027.
  27. Pinto, A. M., Rocha, L. F., & Moreira, A. P. (2013). Object recognition using laser range finder and machine learning techniques. Robotics and Computer-Integrated Manufacturing, 29(1), 1222.CrossRefGoogle Scholar
  28. Rocha, L. F., Malaca, P., Silva, J., Moreira, A. P., & Veiga, G. (2015). Development of a 3D model based part recognition system for industrial applications. In 2015 IEEE international conference on main challenges, industrial technology (ICIT) (pp. 3296–3301).Google Scholar
  29. Rocha, L. F., Ferreira, M., Santos, V., & Moreira, A. P. (2014). Object recognition and pose estimation for industrial applications: A cascade system. Robotics and Computer-Integrated Manufacturing, 30(6), 605–621.CrossRefGoogle Scholar
  30. Sanders, D., Lambert, G., Pevy, L., & Tewkesbury, G. (2009). Improving robotic welding in the shipbuilding industry through the recognition of ship-building parts by pre-locating corners in images. Budapest; 2009 [cited January 7, 2014]. Available from
  31. Schwartz, W. R., & Pedrini, H. (2007). Color textured image segmentation based on spatial dependence using 3D co-occurrence matrices and markov random fields. In 15th international conference in Central Europe on computer graphics, visualization and computer vision, Plzen, Czech Republic (pp. 81–87).Google Scholar
  32. Sharma, M., & Singh, S. (2001). Evaluation of texture methods for image analysis. Intelligent Information Systems Conference, The Seventh Australian and New Zealand, 2001, 11721.Google Scholar
  33. Shenbagavalli, R., & Ramar, K. (2011). Classification of soil textures based on laws features extracted from preprocessing images on sequential and random windows. Bonfring International Journal of Advances in Image Processing, 1, 15–18.Google Scholar
  34. Theodoridis, S., & Koutroumbas, K. (2009). Pattern recognition (4th ed.). Boston, MA: Academic Press.Google Scholar
  35. Veiga, G., Silva, C., Arajo, R., Pires, N., & Siciliano, B. (2013). The ECHORD project proposals analysis Research profiles, collaboration patterns and research topic trends. Expert System with Applications, 40(17), 713240.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Pedro Malaca
    • 1
    • 2
  • Luis F. Rocha
    • 3
    Email author
  • D. Gomes
    • 4
  • João Silva
    • 2
  • Germano Veiga
    • 3
  1. 1.Electrical and Computer Engineering DepartmentUniversity of PortoPortoPortugal
  2. 2.SARKKIS Robotics, Lda.PortoPortugal
  3. 3.INESC-TEC, INESC Technology and SciencePortoPortugal
  4. 4.Mechanical Engineering DepartmentUniversity of CoimbraCoimbraPortugal

Personalised recommendations