Neural Network for Recognition of County Centre Post Codes

  • Hrvoje Gold
  • Mario Samodol
Keywords: routing of postal items, pattern recognition, neural networks


The work represents an artificial neural networkf01· recognitionof county centre post codes. The neural networkPOSTKLAS se1ves as the classification system for the sorting oftwo-digit address data. The de1·eloped model represents atwo-layer network which learns by using backpropagation algorithm.The method of address data recording in the model hasbeen presented. By analysing the sorting results the possibilitywas determined of applying the developed neural network forrecognition even in cases of distorted input pal/erns. The modellingwas done by means of Mat/ab programming ~ystem.


H. Demuth, M. Beale, Neural Network Too/box For Use

with Matlab, User's guide, MathWorks, 1993.

H. Gold, Z. Kavran, D. Kovacevic, 'Recognition of

geometrical properties of traffic signs with artificial neural

network', Suvremeni promet - Proceedings of the 5th

International Symposium Organisation and Safety in

Traffic, Opatija, 1997, Vol. 17, No. 3-4, pp. 330-334 (in


H. Gold, 'Neural networks in traffic and transport'',

Teaching material and instructions for omputer practice,

Fakultet prometnih znanosti, Zagrcb, 1998, p. 107

(in Croatian)

D. Hladnik, 'Automatic reading of address data',

HP-Journal Hrvatske poste, No. 4/99, pp. 15-17 (in


P. D. Wasserman, Neural Computing: The01y and Practice,

Van Nostrand Reinhold, New York, 1985.

How to Cite
Gold H, Samodol M. Neural Network for Recognition of County Centre Post Codes. Promet [Internet]. 1 [cited 2023Mar.26];14(1):1-10. Available from:
Older issues