Skip to main content
SpringerLink
Log in

Extensions of Hopfield Neural Networks for Solving of Stereo-Matching Problem

  • Conference paper
Artificial Intelligence and Soft Computing (ICAISC 2015)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 9119))

Included in the following conference series:

Abstract

Paper considers three Hopfield based architectures in the stereo matching problem solving. Together with classical analogue Hopfield structure two novel architectures are examined: Hybrid-Maximum Neural Network and Self Correcting Neural Network.Energy functions that are crucial for the network performance and working algorithm are also presented.All considered structures are tested to compare their performance features. Two of them are particularly important: accuracy and computational time. For the experiment real and simulated stereo images are used. Obtained results lead to the conclusion about feasibility of considered architectures in the stereo matching problem solving for real time applications.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Abe, S.: Global convergence and suppression of spurious states of the hopfield neural networks. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications 40(4), 246–257 (1993)

    Article  MathSciNet  Google Scholar 

  2. Al-askar, H., Lamb, D., Hussain, A.J., Al-Jumeily, D., Randles, M., Fergus, P.: Predicting financial time series data using artificial immune system-inspired neural networks. Journal of Artifcial Intelligence and Soft Computing Research 5(1), 45–68 (2015)

    Article  Google Scholar 

  3. Alvarez, L., Weickert, J., Sanchez, J., Deriche, R.: Dense disparity map estimation respecting image discontinuities: a PDE and scale-space based approach. Technical Report RR-INRIA/RR-3874-FR+ENG-3874, INRIA, Rocquencourt (2000)

    Google Scholar 

  4. Anand, K., Raman, S., Subramanian, K.: Implementing a neuro fuzzy expert system for optimising the performance of chemical recovery boiler. Journal of Artifcial Intelligence and Soft Computing Research 4(2/3), 249–263 (2014)

    Article  Google Scholar 

  5. Bali, S., Jha, D., Kumar, D., Pham, H.: Fuzzy multi-objective build-or-buy approach for component selection of fault tolerant software system under consensus recovery block scheme with mandatory redundancy in critical modules. Journal of Artifcial Intelligence and Soft Computing Research 4(2/3), 98–119 (2014)

    Article  Google Scholar 

  6. Cierniak, R.: New neural network algorithm for image reconstruction from fan-beam projections. Neurocomputing 72(13-15), 3238–3244 (2009), Hybrid Learning Machines (HAIS 2007)/Recent Developments in Natural Computation (ICNC 2007)

    Google Scholar 

  7. Cpalka, K.: A new method for design and reduction of neuro fuzzy classification systems. IEEE Transactions on Neural Networks 20(4), 701–714 (2009)

    Article  Google Scholar 

  8. Cpalka, K., Rutkowski, L.: Flexible takagi sugeno neuro fuzzy structures for nonlinear approximation. WSEAS Transactions on Systems 5, 1450–1458 (2005)

    MATH  Google Scholar 

  9. Das, P., Pettersson, F., Dutta, S.: Pruned-bimodular neural networks for modelling of strength-ductility balance of hsla steel plates. Journal of Artifcial Intelligence and Soft Computing Research 4(4), 354–372 (2014)

    Article  Google Scholar 

  10. Dunk, A., Haffegee, A., Alexandrov, V.N.: Selection methods for interactive creation and management of objects in 3d immersive environments. In: Sloot, P., van Albada, D., Dongarra, J. (eds.) ICCS. Procedia Computer Science, vol. 1, pp. 2609–2617. Elsevier (2010)

    Google Scholar 

  11. El-Laithy, K., Bogdan, M.: Synchrony state generation: an approach using stochastic synapses. Journal of Artificial Intelligence and Soft Computing Research 1, 17–25 (2011)

    Google Scholar 

  12. Fleet, D., Jepson, A.: Computation of component image velocity from local phase information. International Journal of Computer Vision 5(1), 77–104 (1990)

    Article  Google Scholar 

  13. Gabryel, M., Korytkowski, M., Scherer, R., Rutkowski, L.: Object detection by simple fuzzy classifiers generated by boosting. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part I. LNCS, vol. 7894, pp. 540–547. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  14. Grimson, E.: Computational experiments with a feature based stereo algorithm (1984)

    Google Scholar 

  15. Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press (2004) ISBN: 0521540518

    Google Scholar 

  16. Hopfield, J., Feinstein, D., Palmer, R.: Unlearning has a stabilizing effect in collective memories. Nature 304, 158–159 (1983)

    Article  Google Scholar 

  17. Hopfield, J., Tank, D.: Neural computation of decisions in optimization problems. Biological Cybernetics 52(3), 141–152 (1985)

    MathSciNet  MATH  Google Scholar 

  18. Hopfield, J., Tank, D.: Computing with neural circuits: A model. Science 233, 624–633 (1986)

    Article  Google Scholar 

  19. Katiyar, R., Pathak, V.K., Arya, K.: Human gait recognition system based on shadow free silhouettes using truncated singular value decomposition transformation model. Journal of Artifcial Intelligence and Soft Computing Research 4(4), 283–301 (2014)

    Article  Google Scholar 

  20. Korytkowski, M., Nowicki, R., Rutkowski, L., Scherer, R.: AdaBoost ensemble of DCOG rough–neuro–fuzzy systems. In: Jędrzejowicz, P., Nguyen, N.T., Hoang, K. (eds.) ICCCI 2011, Part I. LNCS, vol. 6922, pp. 62–71. Springer, Heidelberg (2011)

    Chapter  Google Scholar 

  21. Korytkowski, M., Rutkowski, L., Scherer, R.: From ensemble of fuzzy classifiers to single fuzzy rule base classifier. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol. 5097, pp. 265–272. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  22. Laskowski, Ł.: Hybrid-maximum neural network for depth analysis from stereo-image. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010, Part II. LNCS, vol. 6114, pp. 47–55. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  23. Laskowski, Ł.: Objects auto-selection from stereo-images realised by self-correcting neural network. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2012, Part I. LNCS, vol. 7267, pp. 119–125. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  24. Laskowski, L.: A novel hybrid-maximum neural network in stereo-matching process. Neural Computing and Applications 23(7-8), 2435–2450 (2013)

    Article  Google Scholar 

  25. Laskowski, L., Jelonkiewicz, J.: Self-correcting neural network for stereo-matching problem solving. Fundamenta Informaticae 138, 1–26 (2015)

    Article  MathSciNet  Google Scholar 

  26. Lee, J.J., Shim, J.C., Ha, Y.H.: Stereo correspondence using the hopfield neural network of a new energy function. Pattern Recognition 27(11), 1513–1522 (1994)

    Article  Google Scholar 

  27. Lee, S., Park, J.: Dual-mode dynamics neural network for combinatorial optimization. Neurocomputing 8(3), 283–304 (1995), Optimization and Combinatorics, Part I-III

    Google Scholar 

  28. Nishihara, H.K.: Readings in computer vision: Issues, problems, principles, and paradigms, pp. 63–72. Morgan Kaufmann Publishers Inc., San Francisco (1987)

    Google Scholar 

  29. Nowicki, R., Pokropińska, A.: Information criterions applied to neuro-fuzzy architectures design. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 332–337. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

  30. Nowicki, R., Rutkowska, D.: Neuro–fuzzy systems based on Gödel and Sharp implication. In: Proceedings of Intern. Conference Application of Fuzzy Systems and Soft Computing — ICAFS 2000, Siegen, Germany, pp. 232–237 (June 2000)

    Google Scholar 

  31. Nowicki, R., Scherer, R., Rutkowski, L.: A method for learning of hierarchical fuzzy systems. In: Sincak, P., et al. (eds.) Intelligent Technologies – Theory and Applications, pp. 124–129. IOS Press, Amsterdam (2002)

    Google Scholar 

  32. Pajares, G., Cruz, J., Aranda, J.: Relaxation by hopfield network in stereo image matching. Pattern Recognition 31(5), 561–574 (1998)

    Article  Google Scholar 

  33. Paragios, N., Deriche, R.: Geodesic active regions and level set methods for motion estimation and tracking. Computer Vision and Image Understanding 97(3), 259–282 (2005)

    Article  Google Scholar 

  34. Redi, J., Gastaldo, P., Zunino, R.: A two-layer neural system for reduced-reference visual quality assessment. Journal of Artificial Intelligence and Soft Computing Research 1, 27–41 (2011)

    Google Scholar 

  35. Rutkowski, L., Przybył, A., Cpałka, K., Er, M.J.: Online speed profile generation for industrial machine tool based on neuro-fuzzy approach. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010, Part II. LNCS (LNAI), vol. 6114, pp. 645–650. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  36. Rygał, J., Najgebauer, P., Nowak, T., Romanowski, J., Gabryel, M., Scherer, R.: Properties and structure of fast text search engine in context of semantic image analysis. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2012, Part I. LNCS, vol. 7267, pp. 592–599. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  37. Scherer, R.: Neuro-fuzzy relational systems for nonlinear approximation and prediction. Nonlinear Analysis 71, e1420–e1425 (2009)

    Google Scholar 

  38. Scherer, R., Rutkowski, L.: A fuzzy relational system with linguistic antecedent certainty factors. In: Rutkowski, Kacprzyk (eds.) Proceedings of the Sixth International Conference on Neural Network and Soft Computing, Zakopane, Poland, June 11-15, 2002. Advances in Soft Computing, pp. 563–569. Springer, Physica-Verlag (2003)

    Google Scholar 

  39. Scherer, R., Rutkowski, L.: Neuro-fuzzy relational classifiers. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 376–380. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

  40. Singh, M., Hassan, M.: Hierarchical optimisation for non-linear dynamical systems with non-separable cost functions. Automatica 14(1), 99–101 (1978)

    Article  Google Scholar 

  41. Starczewski, J., Scherer, R., Korytkowski, M., Nowicki, R.: Modular type-2 neuro-fuzzy systems. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds.) PPAM 2007. LNCS, vol. 4967, pp. 570–578. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  42. Sun, C.: Fast algorithms for stereo matching and motion estimation. In: Australia-Japan Advanced Workshop on Computer Vision, September 9-11 (2003)

    Google Scholar 

  43. Sun, C., Jones, R., Talbot, H., Wu, X., Cheong, K., Beare, R., Buckley, M., Berman, M.: Measuring the distance of vegetation from powerlines using stereo vision. ISPRS Journal of Photogrammetry and Remote Sensing 60(4), 269–283 (2006)

    Article  Google Scholar 

  44. Takefuji, Y., Lee, K.C., Aiso, H.: An artificial maximum neural network: a winner-take-all neuron model forcing the state of the system in a solution domain. Biological Cybernetics 67(3), 243–251 (1992)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Engineering, Czestochowa University of Technology, Czestochowa, Poland

    Łukasz Laskowski & Jerzy Jelonkiewicz

  2. Department of Computer Science, Meiji University, Chiyoda, Japan

    Yoichi Hayashi

Authors
  1. Łukasz Laskowski
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jerzy Jelonkiewicz
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yoichi Hayashi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Łukasz Laskowski .

Editor information

Editors and Affiliations

  1. Częstochowa University of Technology, Częstochowa, Poland

    Leszek Rutkowski

  2. Częstochowa University of Technology, Częstochowa, Poland

    Marcin Korytkowski

  3. Częstochowa University of Technology, Częstochowa, Poland

    Rafal Scherer

  4. AGH University of Science and Technology, Krakow, Poland

    Ryszard Tadeusiewicz

  5. University of California, Berkeley, California, USA

    Lotfi A. Zadeh

  6. University of Louisville, Louisville, Kentucky, USA

    Jacek M. Zurada

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Laskowski, Ł., Jelonkiewicz, J., Hayashi, Y. (2015). Extensions of Hopfield Neural Networks for Solving of Stereo-Matching Problem. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L., Zurada, J. (eds) Artificial Intelligence and Soft Computing. ICAISC 2015. Lecture Notes in Computer Science(), vol 9119. Springer, Cham. https://doi.org/10.1007/978-3-319-19324-3_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-19324-3_6

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-19323-6

  • Online ISBN: 978-3-319-19324-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation