Neural Network Based Texture Segmentation Using a Markov Random Field Model

  • Tae Hyung Kim
  • Hyun Min Kang
  • Il Kyu Eom
  • Yoo Shin Kim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3972)


This paper presents a novel texture segmentation method using neural networks and a Markov random field (MRF) model. Multi-scale wavelet coefficients are used as input for the neural networks. The output of the neural network is modeled as a posterior probability. Initially, the multi-scale texture segmentation is performed by the posterior probabilities from the neural networks and MAP (maximum a posterior) classification. Then the MAP segmentation maps are produced at all scales. In order to obtain the more improved segmentation result at the finest scale, our proposed method fuses the multi-scale MAP segmentations sequentially from coarse to fine scales. This is done by computing the MAP segmentation given the segmentation map at one scale and a priori knowledge regarding contextual information which is extracted from the adjacent coarser scale segmentation. In this fusion process, the MRF prior distribution and Gibbs sampler are used, where the MRF model serves as the smoothness constraint and the Gibbs sampler acts as the MAP classifier.


Gibbs Sampler Markov Random Field Coarse Scale Texture Segmentation Markov Random Field Model 
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.
    Chen, C.H., Pau, L.F., Wang, P.S.P. (eds.): The Handbook of Pattern Recognition and Computer Vision, 2nd edn., pp. 207–248. World Scientific Publishing Co, Singapore (1998)Google Scholar
  2. 2.
    Georgeson, M.A.: Spatial Fourier Analysis and Human Vision. In: Southland, N.S. (ed.) Tutorial Essays in Psychology. A Guide to Recent Advance, ch. 2, vol. 2. Lawrence Earlbaum Associate, Hillsdale NJ (1979)Google Scholar
  3. 3.
    Jain, A.K., Farrokhnia, F.: Unsupervised Texture Segmentation Using Gabor Filters. Pattern Recognition 24, 1167–1186 (1991)CrossRefGoogle Scholar
  4. 4.
    Choi, H., Baraniuk, R.G.: Multiscale Image Segmentation Using Wavelet-Domain Hidden Markov Models. IEEE Trans. Image Processong 10(9) (September 2001)Google Scholar
  5. 5.
    Chen, Z., Feng, T.J., Houkes, Z.: Texture Segmentation Based on Wavelet and Kohonen Network for Remotely Sensed Images. In: IEEE Int. Conf. Systems, Man, and Cybernetics, Tokyo, Japan, pp. 816–821 (1999)Google Scholar
  6. 6.
    Jiang, X., Zhao, R.: A New Method of Texture Segmentation. In: IEEE Int. Conf. Neural Networks and Signal Processing, Nanjing, China, December 14-17, pp. 1083–1086 (2003)Google Scholar
  7. 7.
    Duda, O.R., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn., pp. 161–192, 576–582. A Wiley Interscience Publication, Hoboken (2001)MATHGoogle Scholar
  8. 8.
    Kim, K.I., Jung, K., Park, S.H., Kim, H.J.: Support Vector Machines for Texture Classification. IEEE Trans. Pattern Analysis and Machine Intelligence 24(11), 1542–1550 (2002)CrossRefGoogle Scholar
  9. 9.
    Kim, T.H., Eom, I.K., Kim, Y.S.: Texture Segmentation Using Neural Networks and Multi-scale Wavelet Features. In: Wang, L., Chen, K., S. Ong, Y. (eds.) ICNC 2005. LNCS, vol. 3611, pp. 400–409. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Hu, R., Fahmy, M.M.: Texture Segmentation Based on A Hierarchical Markov Random Field Model. Signal Processing 26, 285–305 (1992)CrossRefGoogle Scholar
  11. 11.
    Li, S.Z.: Markov Random Field Modeling in Computer Vision. Springer, New York (1995)Google Scholar
  12. 12.
    Stan, Z.L.: Markov Random Field Modeling in Image Analysis. In: Stan, Z.L. (ed.) Computer Science Workbench, 2nd edn. Springer, Heidelberg (2001)Google Scholar
  13. 13.
    Richard, M.D., Lippmann, R.P.: Neural Network Classifiers Estimate Bayesian A Posteriori Probabilities. Neural Computation 3, 461–483 (1991)CrossRefGoogle Scholar
  14. 14.
    Rojas, R.: Short Proof of The Posterior Probability Property of Classifier Neural Networks. Neural Computation 8, 41–43 (1996)CrossRefGoogle Scholar
  15. 15.
    Reidmiller, M., Braun, H.: A Direct Adaptive Method for Faster Backpropagation Learning: The Rprop Algorithm. In: Proc. of ICNN, San Francisco (1993)Google Scholar
  16. 16.
    Duda, O.R., Hart, P.E., Stork, D.G.: Pattern Classification. 2nd edn. A Wiley Interscience Publication, Hoboken (2002) Revised Chapter Section 2.11Google Scholar
  17. 17.
    Fan, G.L., Xia, X.G.: Improved Hidden Markov Models in The Wavelet-Domain. IEEE Trans. Signal Processong 49(1) (January 2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tae Hyung Kim
    • 1
  • Hyun Min Kang
    • 1
  • Il Kyu Eom
    • 1
  • Yoo Shin Kim
    • 2
  1. 1.Dept. Electronics EngineeringPusan National UniversityBusanRepublic of Korea
  2. 2.Research Institute of Computer, Information and CommunicationPusan National UnivesityBusanRepublic of Korea

Personalised recommendations