Machine Vision and Applications

, Volume 22, Issue 6, pp 947–966 | Cite as

Multi-scale neural texture classification using the GPU as a stream processing engine

  • M. Martínez-Zarzuela
  • F. J. Díaz-Pernas
  • M. Antón-Rodríguez
  • J. F. Díez-Higuera
  • D. González-Ortega
  • D. Boto-Giralda
  • F. López-González
  • I. De La Torre
Original Paper


A neural architecture for texture classification running on the Graphics Processing Unit (GPU) under a stream processing model is presented in this paper. Textural features extraction is done in three different scales, it is based on the computations that take place on the mammalian primary visual pathway and incorporates both structural and color information. Feature vectors classification is done using a fuzzy neural network which introduces pattern analysis for orientation invariant texture recognition. Performance tests are done over a varying number of textures and the entire VisTex database. The intrinsic parallelism of the neural system led us to implement the whole architecture to run on GPUs, providing a speed-up between × 16 and × 25 for classifying textures of sizes 128 × 128 and 512 × 512 px with respect to an implementation on the CPU. A comparison of classification rates obtained with other methods is included and shows the great performance of the architecture. An average classification rate of 85.2% is obtained for 167 textures of size 512 × 512 px.


Texture classification Stream processing Visual system GPU Neural processing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Julesz, B., Bergen, J.R.: Textons, the fundamental elements in preattentive vision and perception of textures. In: Readings in Computer Vision: Issues, Problems, Principles, and Paradigms, pp. 243–256. Morgan Kaufmann, San Francisco (1987)Google Scholar
  2. 2.
    Pothos V.K., Theoharatos C., Zygouris E., Economou G.: Distributional-based texture classification using non-parametric statistics. Pattern Anal. Appl. 11(2), 117–129 (2008)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Leung T., Malik J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. Int. J. Comput. Vis. 43(1), 29–44 (2001)CrossRefMATHGoogle Scholar
  4. 4.
    Lazebnik S., Schmid C., Ponce J.: A sparse texture representation using local affine regions, IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1265–1278 (2005) student Member-Lazebnik, Svetlana and Senior Member-Schmid, Cordelia and Fellow-Ponce, JeanCrossRefGoogle Scholar
  5. 5.
    Haralick, R.M., Dinstein, I., Shanmugam, K.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. SMC-3 610–621 (1973)Google Scholar
  6. 6.
    Varma M., Zisserman A.: Unifying statistical texture classification frameworks. Image Vis. Comput. 22(14), 1175–1183 (2004)Google Scholar
  7. 7.
    Speis A., Healey G.: Feature extraction for texture discrimination via random field models with random spatial interaction. IEEE Trans. Image Process. 5(4), 635–645 (1996)CrossRefGoogle Scholar
  8. 8.
    Mellor M., Hong B.-W., Brady M.: Locally rotation, contrast, and scale invariant descriptors for texture analysis. IEEE Trans. Pattern Anal. Mach. Intell. 30(1), 52–61 (2008)CrossRefGoogle Scholar
  9. 9.
    Greenspan, H., Belongie, S., Goodman, R., Perona, P.: Rotation invariant texture recognition using a steerable pyramid. In: Proceedings of the International Conference on Pattern Recognition, pp. 162–167 (1994)Google Scholar
  10. 10.
    Tzagkarakis G., Beferull-lozano B., Tsakalides P.: Rotation-invariant texture retrieval with gaussianized steerable pyramids. IEEE Trans. Image Process. 15, 2702–2718 (2006)CrossRefGoogle Scholar
  11. 11.
    Hubel D.H., Wiesel T.N.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195(1), 215–243 (1968)Google Scholar
  12. 12.
    Obermayer K., Blasdel G.G.: Geometry of orientation and ocular dominance columns in monkey striate cortex. J. Neurosci. 13, 4114–4129 (1993)Google Scholar
  13. 13.
    Weliky M., Bosking W., Fitz Patrick D.: A systematic map of direction preference in primary visual cortex. Nature 379, 725–728 (1996)CrossRefGoogle Scholar
  14. 14.
    Papathomas T., Kashi R., Gorea A.: A human vision based computational model for chromatic texture segregation. Syst. Man Cybern. Part B: Cybern. IEEE Trans. 27(3), 428–440 (1997)CrossRefGoogle Scholar
  15. 15.
    Drimbarean A., Whelan P.F.: Experiments in colour texture analysis. Pattern Recogn. Lett. 22, 1161–1167 (2001)CrossRefMATHGoogle Scholar
  16. 16.
    Poirson A.B., Wandell B.A.: Pattern-color separable pathways predict sensitivity to simple colored patterns. Vis. Res. 36, 515–526 (1996)CrossRefGoogle Scholar
  17. 17.
    Mojsilovic A., Mojsilovic’ R., Kovacevic J., Hu J., Safranek R.J., Member S., Member S., Ganapathy S.K.: Matching and retrieval based on the vocabulary and grammar of color patterns. IEEE Trans. Image Process. 9, 38–54 (2000)CrossRefGoogle Scholar
  18. 18.
    Masquelier, T., Thorpe, S.J.: Unsupervised learning of visual features through spike timing dependent plasticity, PLoS Computat. Biol. 3(2), (2007)Google Scholar
  19. 19.
    Hawkins J., Blakeslee S.: On Intelligence. Holt Paperbacks, London (2005)Google Scholar
  20. 20.
    Antón-Rodríguez M., Díaz-Pernas F.J., Díez-Higuera J.F., Martínez-Zarzuela M., González-Ortega D., Boto-Giralda D.: Recognition of coloured and textured images through a multi-scale neural architecture with orientational filtering and chromatic diffusion. Neurocomputing 72, 3713–3725 (2009)CrossRefGoogle Scholar
  21. 21.
    Díaz-Pernas F.J., Antón-Rodríguez M., Díez-Higuera J.F., Martínez-Zarzuela M., González-Ortega D., Boto-Giralda D.: Texture classification of the entire brodatz database through an orientational-invariant neural architecture. In: Mira, J.M., Ferrández, J.M., Álvarez, J.R., Paz, F., Toledo, F.J. (eds) IWINAC (2). Lecture Notes in Computer Science, pp. 294–303. Springer, Heidelberg (2009)Google Scholar
  22. 22.
    Grossberg S., Williamson J.R.: A self-organizing neural system for learning to recognize textured scenes. Vis. Res. 39, 1385–1406 (1999)CrossRefGoogle Scholar
  23. 23.
    Greenspan H.: Non-parametric texture learning. In: Nayar, S.K., Poggio, T. (eds) Early Visual Learning, Oxford University Press, Oxford (1996)Google Scholar
  24. 24.
    VisTex: Vision Texture Database (Massachusetts Institute of Technology),, last visit, Feb. 2009 (1995)
  25. 25.
    Zomaya, A.Y. (eds): Handbook of Nature-Inspired and Innovative Computing: Integrating Classical Models with Emerging Technologies. Springer, New York (2006)Google Scholar
  26. 26.
    Moore, G. E.: Cramming More Components onto Integrated Circuits. Reprinted from Electronics, vol. 38(8), pp.114 ff., April 19, 1965. Solid-State Circuits Newsletter, vol. 20(3) pp. 33–35. IEEE, New York (2006)Google Scholar
  27. 27.
    NVIDIA, NVIDIA CUDA Programming Guide 2.3 (2009)Google Scholar
  28. 28.
    Owens J.D., Houston M., Luebke D., Green S., Stone J.E., Phillips J.C.: GPU computing. Proc. IEEE 96(5), 879–899 (2008)CrossRefGoogle Scholar
  29. 29.
    Fung, J., Mann, S.: Using graphics devices in reverse: Gpu-based image processing and computer vision. In: Multimedia and Expo, 2008 IEEE International Conference on, pp. 9–12 (2008)Google Scholar
  30. 30.
    Luebke, D.: Graphics hardware & gpu computing: past, present, and future. In: GI ’09: Proceedings of Graphics Interface 2009, pp. 1–1. Canadian Information Processing Society, Toronto (2009)Google Scholar
  31. 31.
    Owens J.D., Luebke D., Govindaraju N., Harris M., Krüger J., Lefohn A.E., Purcell T.J.: A survey of general-purpose computation on graphics hardware. Comp. Graphics Forum 26(1), 80–113 (2007)CrossRefGoogle Scholar
  32. 32.
    Owens, J.: Streaming architectures and technology trends. In: Pharr, M. (ed.) GPU Gems 2, Chap. 29, pp. 457–470. Addison Wesley, New York (2005)Google Scholar
  33. 33.
    Segal, M., Akeley, K.: The design of the opengl graphics interface. Technical report. Silicon Graphics Computer Systems (1994)Google Scholar
  34. 34.
    Carpenter G.A., Grossberg S., Markuzon N., Reynolds J.H., Rosen D.B.: Fuzzy artmap: a neural network architecture for incremental supervised learning of analog multidimensional maps. Neural Netw. IEEE Trans. 3(5), 698–713 (1992)CrossRefGoogle Scholar
  35. 35.
    Hodgkin A.L.: The Conduction of the Nerve Impulse. WB Saunders, Springfield (1964)Google Scholar
  36. 36.
    Hubel D.H., Livingstone M.S.: Color and contrast sensitivity in the lateral geniculate body and primary visual cortex of the macaque monkey. Neuroscience 10(7), 2223–2237 (1990)Google Scholar
  37. 37.
    Schwartz S.H.: Visual Perception: A Clinical Orientation. 3rd edn. McGraw-Hill, New York (2004)Google Scholar
  38. 38.
    Díaz-Pernas, F.J., Antón-Rodríguez, M., Martínez-Zarzuela, M., Díez-Higuera, J.F., González-Ortega, D., Boto-Giralda, D.: Multiple scale neural architecture for enhancing regions in the colour image segmentation process. Exp. Syst. (2010, in press)Google Scholar
  39. 39.
    IPP: Intel Integrated Performance Primitives, Intel multimedia and data processing software library. Última visita (Feb. 2008)Google Scholar
  40. 40.
    Lefohn A., Kniss J., Owens J.: Implementing efficient parallel data structures on gpus. In: Pharr, M. (eds) GPU Gems 2, Chap. 33, pp. 521–544. Addison Wesley, New York (2005)Google Scholar
  41. 41.
    Harris M.: Mapping computational concepts to gpus. In: Pharr, M. (eds) GPU Gems 2, Chap. 31, pp. 493–508. Addison Wesley, New York (2005)Google Scholar
  42. 42.
    Woo M. Davis, Sheridan M.B.: OpenGL Programming Guide: The Official Guide to Learning OpenGL, Version 1.2. Addison-Wesley, Boston (1999)Google Scholar
  43. 43.
    Kurmyshev E.V., Sanchez-Yanez R.E.: Comparative experiment with colour texture classifiers using the ccr feature space. Pattern Recogn. Lett. 26(9), 1346–1353 (2005)CrossRefGoogle Scholar
  44. 44.
    Sengur A.: Wavelet transform and adaptive neuro-fuzzy inference system for color texture classification. Expert Syst. Appl. 34(3), 2120–2128 (2008)CrossRefGoogle Scholar
  45. 45.
    Permuter H., Francos J., Jermyn I.: A study of gaussian mixture models of color and texture features for image classification and segmentation. Pattern Recogn. 39(4), 695–706 (2006) Graph-based RepresentationsCrossRefMATHGoogle Scholar
  46. 46.
    Mäenpää T., Pietikäinen M.: Classification with color and texture: jointly or separately?. Pattern Recogn. 37(8), 1629–1640 (2004)CrossRefGoogle Scholar
  47. 47.
    Mäenpää, T., Pietikäinen, M., Viertola, J.: Separating color and pattern information for color texture discrimination. In: Proceedings of the 16th International Conference on Pattern Recognition, pp. 668–671 (2002)Google Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • M. Martínez-Zarzuela
    • 1
  • F. J. Díaz-Pernas
    • 1
  • M. Antón-Rodríguez
    • 1
  • J. F. Díez-Higuera
    • 1
  • D. González-Ortega
    • 1
  • D. Boto-Giralda
    • 1
  • F. López-González
    • 1
  • I. De La Torre
    • 1
  1. 1.Edificio de Tecnologías de la Información y las TelecomunicacionesValladolidSpain

Personalised recommendations