License Plate Location Based on Simplified Pulse Coupled Neural Network and Comprehensive Feature

DOI

10.2991/csic-15.2015.39How to use a DOI?

Keywords

License plate location, Pulse coupled neural network, Morphology, Color analysis, Line scan, Vertical projection

Abstract

License plate location is the key of the license plate recognition system. In order to accurately to locate the license plate region in the complex environment, this paper puts forward a license plate locating method based on simplified pulse coupled neural network and comprehensive feature. Firstly, pre-processing and morphological filtering on the vehicle image, and extract the license plate candidate area based on the structure features of the license. Then, doing color analysis in the candidate area of HSV color space to achieve coarse location of license plate. After that, using simplified Pulse Coupled Neural Network (PCNN) for image binarization and using the radon transform of license plate to tilt correction. Finally, get the accurate localization of the correction results of license plate by line scan and vertical projection. The experimental results show that the algorithm has high accuracy, good robustness and can meet the real-time requirement.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Guangjun Xie
AU  - Xiaoxi Ren
PY  - 2015/07
DA  - 2015/07
TI  - License Plate Location Based on Simplified Pulse Coupled Neural Network and Comprehensive Feature
BT  - Proceedings of the 2015 International Conference on Computer Science and Intelligent Communication
PB  - Atlantis Press
SP  - 163
EP  - 166
SN  - 2352-538X
UR  - https://doi.org/10.2991/csic-15.2015.39
DO  - 10.2991/csic-15.2015.39
ID  - Xie2015/07
ER  -