Advertisement

Modified Dendrite Morphological Neural Network Applied to 3D Object Recognition

  • Humberto Sossa
  • Elizabeth Guevara
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7914)

Abstract

In this paper a modified dendrite morphological neural network (DMNN) is applied for recognition and classification of 3D objects. For feature extraction, the first two Hu’s moment invariants are calculated based on 2D binary images, as well as the mean and the standard deviation obtained on 2D grayscale images. These four features were fed into a DMNN for classification of 3D objects. For testing, COIL-20 image database and a generated dataset were used. A comparative analysis of the proposed method with MLP and SVM is presented and the results reveal the advantages of the modified DMNN. An important characteristic of the proposed recognition method is that because of the simplicity of calculation of the extracted features and the DMNN, this method can be used in real applications.

Keywords

Dendrite morphological neural network efficient training 3D object recognition classification 

References

  1. 1.
    Wöhler, C.: 3D Computer Vision: Efficient Methods and Applications. Springer (2012)Google Scholar
  2. 2.
    Grauman, K., Leibe, B.: Visual Object Recognition. Morgan & Claypool (2011)Google Scholar
  3. 3.
    Sossa, H., Guevara, E.: Efficient training for dendrite morphological neural networks. Submitted to Neurocomputing - Elsevier JournalGoogle Scholar
  4. 4.
    Nene, D., Nayar, S., Murase, H.: Columbia object image library: COIL (1996)Google Scholar
  5. 5.
    Hu, M.K.: Visual pattern recognition by moment invariants. IRE Transactions on Information Theory 8, 179–187 (1962)zbMATHGoogle Scholar
  6. 6.
    González, R., Woods, R.: Digital Image Processing. Pearson (2007)Google Scholar
  7. 7.
    Ritter, G.X., Iancu, L., Urcid, G.: Morphological perceptrons with dendritic structure. In: 12th IEEE International Conference in Fuzzy Systems (FUZZ 2003), vol. 2, pp. 1296–1301 (2003)Google Scholar
  8. 8.
    Ritter, G.X., Urcid, G.: Lattice algebra approach to single-neuron computation. IEEE Transactions on Neural Networks 14(2), 282–295 (2003)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Davidson, J.L., Hummer, F.: Morphology neural networks: An introduction with applications. Circuits Systems Signal Process 12(2), 177–210 (1993)MathSciNetzbMATHCrossRefGoogle Scholar
  10. 10.
    Ritter, G.X., Sussner, P.: An introduction to morphological neural networks. In: Proceedings of the 13th International Conference on Pattern Recognition, vol. 4, pp. 709–717 (1996)Google Scholar
  11. 11.
    Sussner, P.: Morphological perceptron learning. In: IEEE ISIC/CIRA/ISAS Joint Conference, pp. 477–482 (1998)Google Scholar
  12. 12.
    Piñeiro Colón, R.C., Ortiz, J.L.: Evolutionary Training of Morphological Neural Networks. PhD thesis, Electrical and Computer Engineering Department. University of Puerto Rico, Mayagüez CampusGoogle Scholar
  13. 13.
    Lima, C.A.M., Coelho, A.L.V., Silva, M.E.S., Gudwin, R.R., Von Zuben, F.J.: Hybrid training of morphological neural networks: A comparative study. Technical report, DCA-FEEC-UnicampGoogle Scholar
  14. 14.
    De Aráujo, R., Madeiro, F., De Sousa, R.P., Pessoa, L.F.C.: Modular morphological neural network training via adaptive genetic algorithm for designing translation invariant operators. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), vol. 2, pp. 873–876 (2006)Google Scholar
  15. 15.
    Raducanu, B., Graña, M., Sussner, P.: Morphological neural networks for vision based self-localization. In: IEEE International Conference on Robotics and Automation, pp. 2059–2064 (2001)Google Scholar
  16. 16.
    Nong, Y., Hao, W., Changyong, W., Fanming, L., Lide, W.: Morphological neural networks for automatic target detection by simulated annealing learning algorithm. Science in China (Series F) 46, 262–278 (2003)zbMATHGoogle Scholar
  17. 17.
    Villaverde, I., Graña, M., D’Anjou, A.: Morphological neural networks for localization and mapping. In: IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA 2006), pp. 9–14 (2006)Google Scholar
  18. 18.
    Roberson, C., Dankel II, D.D.: A morphological neural network approach to information retrieval. In: Twentieth International Florida Artificial Intelligence Research Society Conference, pp. 184–185 (2007)Google Scholar
  19. 19.
    Cheng-Tian, S., Ke-Yong, W.: Image target detection using morphological neural network. In: International Conference on Computational Intelligence and Security, pp. 234–236 (2009)Google Scholar
  20. 20.
    Sussner, P., Esmi, E.L.: Morphological perceptrons with competitive learning: Lattice-theoretical framework and constructive learning algorithm. Information Sciences 181, 1929–1950 (2011)MathSciNetzbMATHCrossRefGoogle Scholar
  21. 21.
    Segev, I.: Dendritic processing. In: The Handbook of Brain Theory and Neural Networks, pp. 282–289 (1998)Google Scholar
  22. 22.
    Barrón, R., Sossa, H., Cortés, H.: Morphological neural networks with dendrite computation: A geometrical approach. In: Sanfeliu, A., Ruiz-Shulcloper, J. (eds.) CIARP 2003. LNCS, vol. 2905, pp. 588–595. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  23. 23.
    Valle, M.E.R., Pimenta, M.A.: Perceptrón morfológico de camada única. Technical report, Department of Mathematics of the State University of Londrina, Brazil (2005)Google Scholar
  24. 24.
    Ritter, G.X., Schmalz, M.S.: Learning in lattice neural networks that employ dendritic computing. In: IEEE International Conference on Fuzzy Systems, Vancouver, BC, Canada, pp. 7–13 (2006)Google Scholar
  25. 25.
    Ritter, G.X., Urcid, G.: Learning in lattice neural networks that employ dendritic computing. Computational Intelligence Based on Lattice Theory 67, 25–44 (2007)CrossRefGoogle Scholar
  26. 26.
    Chyzhyk, D., Graña, M.: Optimal hyperbox shrinking in dendritic computing applied to Alzheimer’s disease detection in MRI. In: Corchado, E., Snášel, V., Sedano, J., Hassanien, A.E., Calvo, J.L., Ślęzak, D. (eds.) SOCO 2011. AISC, vol. 87, pp. 543–550. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  27. 27.
    Graña, M.: Special issue on: Lattice computing and natural computing. Neurocomputing 72(10-12), 2065–2066 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Humberto Sossa
    • 1
  • Elizabeth Guevara
    • 1
  1. 1.Instituto Politécnico Nacional - CICMexico, D. F.Mexico

Personalised recommendations