Automatic Classification System of Marble Slabs in Production Line According to Texture and Color Using Artificial Neural Networks

  • Juan Martńez-Cabeza-de-Vaca-Alajarín
  • Luis-Manuel Tomás-Balibrea
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1689)


This article describes the algorithms and the mechatronic system developed for the clustering and classification of marble slabs on production line according to their texture. The method used for the recognition of textures is based on the Sum and Difference Histograms, a faster version of the Co-occurrence Matrices, and the classifier has been implemented by using an LVQ neural network. For each pattern (a marble slab color image), a set of statistical, texture-dependant, parameters is extracted. The input of the classifier (the LVQ network) is the set of parameters calculated before, normalized in the range 0, 1, which forms a vector that characterize the pattern shown to the net; the desired output of the network is the class where the pattern belongs to (supervised learning). In our tests, seven different color spaces were used, each one with three different neighbourhoods of pixels. The selected samples chosen for testing the algorithms have been marble slabs of “Crema Marl Sierra de la Puerta” type. The neural network has been implemented by using MATLAB.


Grey Level Color Space Target Class Very Large Scale Integration Mechatronic System 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Garceráan-Hernández, V., García-Pérez, L. G., Clemente-Pérez, P., Tomás-Balibrea, L. M., Puyosa-Piña, H. D.: Traditional and neural networks algorithms: applications to the inspection of marble slabs. IEEE International Conference on Systems, Man and Cybernetics; 0-7803-2559-1, Vancouver (Canada) (1995) 3960–3965Google Scholar
  2. 2.
    Van de Wouwer, G.: Wavelets for multiscale texture analysis. University of Antwerpen (1998)Google Scholar
  3. 3.
    Unser, M.: Sum and difference histograms for texture classification. IEEE Trans. on PAMI Vol.PAMI-8 No.1 (1986) 118–125Google Scholar
  4. 4.
    Haralick. R. M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. on SMC Vol.SMC-3 No.6 (1973) 610–621Google Scholar
  5. 5.
    Haralick, R. M.: Statistical and structural approaches to texture. Proc. IEEE Vol. 67No.5 (1979) 786–804CrossRefGoogle Scholar
  6. 6.
    Gotlieb, C. C., Kreyszig, H. E.: Texture descriptors based on co-occurrence matrices. Computer Vision, Graphics and Image Processing 51 (1990) 70–86CrossRefGoogle Scholar
  7. 7.
    Kohonen, T.: The self-organizing map. Proc. IEEE Vol.78No.9 (1990) 1464–1480CrossRefGoogle Scholar
  8. 8.
    Demuth, H., Beale, M.: Neural network toolbox user’s guide. The Mathworks Inc. (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Juan Martńez-Cabeza-de-Vaca-Alajarín
    • 1
  • Luis-Manuel Tomás-Balibrea
    • 1
  1. 1.Grupo de Visión y RobóticaE.T.S.I. Industriales, Universidad de MurciaCartagena (Murcia)Spain

Personalised recommendations