Pattern Recognition Without Feature Extraction Using Probabilistic Neural Network

  • Övünç Polat
  • Tülay Yıldırım
Part of the Lecture Notes in Control and Information Sciences book series (LNCIS, volume 345)


This article describes an approach to automatically recognize patterns such as 3D objects and handwritten digits based on a database. The designed system can be used for both 3D object recognition from 2D poses of the object and handwritten digit recognition applications. The system does not require any feature extraction stage before the recognition. Probabilistic Neural Network (PNN) is used for the recognition of the patterns. Experimental results show that pattern recognition by the proposed method improves the recognition rate considerably. The system has been compared to other network structures in terms of speed and accuracy and has shown better performance in simulations.


Input Image Object Recognition Recognition Rate Convolutional Neural Network Probabilistic Neural Network 
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.
    Li, B.Q., Li, B.X.: Building Pattern Classifiers Using Convolutional Neural Networks. IJCNN’ 99. International Joint Conference on Neural Networks. 5 (1999) 3081–3085Google Scholar
  2. 2.
    Goh, T. C.: Probabilistic Neural Network for Evaluating Seismic Liquefaction Potential. Can. Geotech. J., 39 (2002) 219–232CrossRefGoogle Scholar
  3. 3.
    Egmont-Petersen, M., de Ridder, D., Handels, H.: Image Processing with Neural Networks — A Review. The Journal of the Pattern Recognition Society, 35(10) (2002) 2279–2301zbMATHCrossRefGoogle Scholar
  4. 4.
    Zhao, L.W., Luo, S.W., Liao, L.Z.: 3D Object Recognition and Pose Estimation Using Kernel PCA. Proceedings of 2004 International Conference on Machine Learning and Cybernetics, 5 (2004) 3258–3262Google Scholar
  5. 5.
    Okamoto, J., Jr., Milanova, M., Bueker, U.: Active Perception System for Recognition of 3D Objects in Image Sequences. 5th International Workshop on Advanced Motion Control. AMC’ 98-Coimbra. 29 (1998) 700–705Google Scholar
  6. 6.
    Polat, O., Tavsanoglu, V.: 3-D Object Recognition Using 2-D Poses Processed by CNNs and a GRNN. Proc. of 2005 Turkish Symposium Artificial Intelligence and Neural Networks. Cesme, Turkey (June 2005)Google Scholar
  7. 7.
    Nebauer, C.: Evaluation of Convolutional Neural Networks for Visual Recognition. IEEE Transactions on Neural Networks, Vol. 9, Issue 4. (July 1998) 685–696CrossRefGoogle Scholar
  8. 8.
    Fasel, B.: Head-pose Invariant Facial Expression Recognition Using Convolutional Neural Networks. Proc. of 2002 Fourth IEEE International Conference on Multimodal Interfaces. (2002) 529–534Google Scholar
  9. 9.
    Simard, P.Y., Steinkraus, D., Platt, J.C.: Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis. Proc. of the 2003 Seventh International Conference on Document Analysis and Recognition, (2003) 958–963Google Scholar
  10. 10.
    Comes, B., Kelemen, A.: Probabilistic Neural Network Classification for Microarraydata. Proceedings of the International Joint Conference on Neural Networks, 3 (2003) 1714–1717Google Scholar
  11. 11.
    Parzen, E.: On Estimation of A Probability Density Function and Model, Annals of Mathematical Statistics, 36 (1962) 1065–1076MathSciNetGoogle Scholar
  12. 12.
    Sameer, A. N., Shree, K. N., Hiroshi M.: Columbia Object Image Library (COIL-100). Technical Report No. CUCS-006-96, Department of Computer Science Columbia University New York, N.Y. 10027Google Scholar
  13. 13.
    Available in Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Övünç Polat
    • 1
  • Tülay Yıldırım
    • 1
  1. 1.Electronics and Communications Engineering DepartmentYıldız Technical UniversityBesiktas, IstanbulTurkey

Personalised recommendations