Parameter influence of pulse coupled neural network for image recognition

• Autorzy: Forgac, R. , Mokris, I.
• Języki publikacji: EN

Abstrakty

EN

The paper describes basic parameters of the Pulse coupled neural network (PCNN) and their influence to feature generation for image recognition, especially. The basic PCNN parameters are linking radius, linking coefficient and PCNN kernel type. Determination of the optimal values of these parameters is a difficult problem, because they are dependent on input image set. In many cases these parameters can be set experimentally. It is very important to set up these parameters correctly, because they have influence on duration of feature generation process, on the number of features for the needed image description and on the quality and exactness of generated features.

Słowa kluczowe

PL

PCNN; impulsująca sieć neuronowa; sieci neuronowe; rozpoznawanie obrazów

EN

PCNN; pulse coupled neural network (PCNN); neural networks; image recognition

• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2001
• Tom: Vol. 9, nr 2
• Strony: 31-44
• Opis fizyczny: Bibliogr. 11 poz.

Twórcy

autor

Forgac, R.

• Faculty of Finance, Matej Bel University, Banska Bystrica, Slovakia

autor

Mokris, I.

• Faculty of Finance, Matej Bel University, Banska Bystrica, Slovakia

Bibliografia

• [1] Becanovic, V.: PCNN Toolbox for MATLAB ver. 3.1.3, 1998.
• [2] Eckhorn, R. et al.: Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex. Neural Computation, 1990, Vol. 2, pp. 293-307.
• [3] Forgač, R., Mokriš, I.: Invariant Image Recognition Using Distributed Neural Networks. In: INES’99 - 3rd IEEE International Conference on Intelligent Engineering Systems, Stará Lesná, 1999, pp. 105-109.
• [4] Forgač, R., Mokriš, I.: Invariant Representation of Images by Pulse Coupled Neural Network. In: E-ISCI’2000 - European Symposium on Computational Intelligence, Košice, Springer-Verlag, 2000, pp. 33-38.
• [5] Johnson, J. L.: Pulse Coupled Neural Nets: Translation, Rotation, Scale, Distortion and Intensity Signal Invariance for Images. Applied Optics, 1994, Vol. 33, pp. 6239-6253.
• [6] Johnson, J. L., Padgett, M. L.: PCNN Models and Applications. IEEE Transactions on Neural Networks, 1999, Vol. 2, No. 3, pp. 480-498.
• [7] Johnson, L. J., Ritter, D.: Observation of Periodic Waves in a Pulse-coupled Neural Network. Optics Letters, 1993, Vol. 18, No. 15, pp. 1253-1255.
• [8] Kuntimad, G., Ranganath, H. S.: Perfect Image Segmentation Using Pulse Coupled Neural Networks. IEEE Transactions on Neural Networks, 1999, Vol. 2, No. 3, pp. 591-598.
• [9] Kinser, J. M., Lindblad, T.: Implementation of Pulse-Coupled Neural Networks in the CNAPS Environment. IEEE Transactions on Neural Networks, 1999, Vol. 2, No. 3, pp. 584-590.
• [10] Kinser, J. M., Johnson, J. L.: Stabilized Input with a Feedback Pulse-Coupled Neural Network, submitted to Optical Engineering.
• [11] Ranganath, H. S., Kuntimad, G.: Object Detection Using Pulse Coupled Neural Networks. IEEE Transactions on Neural Networks, 1999, Vol. 2, No. 3, pp. 615-621. Ranganath, H. S., Kuntimad, G.: Iterative segmentation using Pulse Coupled Neural Networks. SPIE, Vol. 2760, pp. 543-554.