MRF-MBNN: A Novel Neural Network Architecture for Image Processing | SpringerLink
Skip to main content
Springer Nature Link
Log in

MRF-MBNN: A Novel Neural Network Architecture for Image Processing

  • Conference paper
Advances in Neural Networks – ISNN 2005 (ISNN 2005)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 3497))

Included in the following conference series:

  • 1654 Accesses

Abstract

Contextual information and a priori knowledge play important roles in image segmentation based on neural networks. This paper proposed a method for including contextual information in a model-based neural network (MBNN) that has the advantage of combining a priori knowledge. This is achieved by including Markov random field (MRF) into the MBNN and this novel neural network is termed as MRF-MBNN. Then the proposed method is applied to segmenting the images. Experimental results indicate the MRF-MBNN is superior to the MBNN in image segmentation. This study is a successful attempt of incorporating contextual information and a prior knowledge into neural networks to segment images.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Egmont-Petersen, M., De Ridder, D., Handels, H.: Image Processing with Neural Networks – A Review. Pattern Recognition 35, 2279–2301 (2002)

    Article  MATH  Google Scholar 

  2. Perlovsky, L.I., McManus, M.M.: Maximum Likelihood Neural Networks for Sensor Fusion and Adaptive Classification. Neural Networks 4, 89–102 (1991)

    Article  Google Scholar 

  3. Perlovsky, L.I., Schoendorf, W.H., Burdick, B.J., Type, D.M.: Model-based Neural Network for Target Detection in SAR Image. IEEE Trans. Image Processing 6, 203–215 (1997)

    Article  Google Scholar 

  4. Caelli, T.M., McG.Squire, D., Wild, T.P.J.: Model-based Neural Networks. Neural Networks 6, 613–625 (1993)

    Google Scholar 

  5. Cai, N., Hu, K.H., Xiong, H.T., Li, S.Y., Su, W.F., Zhu, F.S.: Image Segmentation of G Bands of Triticum Monococcum Chromosomes Based on the Model-based Neural Network. Pattern Recognition Letter 25, 319–329 (2004)

    Article  Google Scholar 

  6. Besag, J.: Spatial Interaction and Statistical Analysis of Lattice Systems. Acad. R. Stat. Soc. B 36, 721–741 (1974)

    MathSciNet  Google Scholar 

  7. Geman, S., Geman, D.: Stochastic Relaxation, Gibbs Distribution, and the Bayesian Restoration of Images. IEEE Trans. Pattern Anal. Machine Intell, PAMI 6, 721–741 (1984)

    Article  MATH  Google Scholar 

  8. Saquib, S.S., Bouman, C.A., Sauer, K.: ML Parameter Estimation for Markov Random Fields with Applications to Bayesian Tomography. IEEE Trans. Image Processing 7, 1029–1044 (1998)

    Article  Google Scholar 

  9. Perlovsky, L.I.: Multiple Sensor Fusion and Neural Networks. DARPA Neural Network Study, MIT/Lincoln Lab, Lexington, MA (1987)

    Google Scholar 

  10. Kashyap, R.L.: Analysis and Synthesis of Image Patterns by Spatial Interaction Models. In: Kanal, L.N., Rosenfeld, A. (eds.) Progress in Pattern Recognition, North-Holland, Amsterdam (1981)

    Google Scholar 

  11. Comer, M.L., Delp, E.J.: Segmentation of Textured Images Using a Multiresolution Gaussian Autoregressive Model. IEEE Trans. Image Processing 8, 408–420 (1999)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, 1954 Huashan Road, Shanghai, 200030, China

    Nian Cai & Jie Yang

  2. Lab of Image Analysis and Pattern Recognition, Institute of Biophysics, Chinese Academy of Sciences, 15 Datun Road, Chaoyang District, Beijing, 100101, China

    Kuanghu Hu & Haitao Xiong

Authors
  1. Nian Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kuanghu Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Haitao Xiong
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, China

    Jun Wang

  2. The Key Laboratory of Optoelectric Technology & Systems, Ministry of Education, China

    Xiao-Feng Liao

  3. Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, 610054, Chengdu, P.R. China

    Zhang Yi

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Cai, N., Yang, J., Hu, K., Xiong, H. (2005). MRF-MBNN: A Novel Neural Network Architecture for Image Processing. In: Wang, J., Liao, XF., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3497. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427445_109

Download citation

  • DOI: https://doi.org/10.1007/11427445_109

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-25913-8

  • Online ISBN: 978-3-540-32067-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics