Neural Network Based Texture Segmentation Using a Markov Random Field Model
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.
KeywordsGibbs Sampler Markov Random Field Coarse Scale Texture Segmentation Markov Random Field Model
Unable to display preview. Download preview PDF.
- 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.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
- 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.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.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
- 11.Li, S.Z.: Markov Random Field Modeling in Computer Vision. Springer, New York (1995)Google Scholar
- 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
- 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.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.Fan, G.L., Xia, X.G.: Improved Hidden Markov Models in The Wavelet-Domain. IEEE Trans. Signal Processong 49(1) (January 2001)Google Scholar