Real-Time Car License Plate Recognition Improvement Based on Spatiognitron Neural Network

Authors:
Dariusz Król;Maciej Maksym
Affiliations:
Institute of Applied Informatics, Wrocław University of Technology, Wrocław, Poland 50-370;Institute of Applied Informatics, Wrocław University of Technology, Wrocław, Poland 50-370
Venue:
IEA/AIE '08 Proceedings of the 21st international conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems: New Frontiers in Applied Artificial Intelligence
Year:
2008

Citing 7
Cited 0

A Survey of Methods and Strategies in Character Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
An efficient method of license plate location

Pattern Recognition Letters
Towards a Multinational Car License Plate Recognition System

Machine Vision and Applications
RETRACTED: A smart access control using an efficient license plate location and recognition approach

Expert Systems with Applications: An International Journal
Region-based license plate detection

Journal of Network and Computer Applications
A neural-network-based approach to detecting rectangular objects

Neurocomputing
A hybrid method for robust car plate character recognition

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article describes real-time car license plate recognition (CLPR) system based on spatiognitron neural network comparing to other ANPR/CLPR systems. Our neural network architecture is very efficient and improves whole recognition process. Spatiognitron neural network is inspired by biological neural structure --- the mammalian primary visual cortex. This theory describes so called receptive fields, which are responsible for recognizing different kinds of features in the input image. This network also uses analog-like recognition method. In this method, the neural network responds in real-time. This is connected with reorganizing classical paradigm of image recognition process. The character of recognition stage is performed before the image segmentation. This approach seems to be more logical and it was certified in many quality tests of recognition process in commercial NeuroCar system.