Use of the Hough transformation to detect lines and curves in pictures
Communications of the ACM
Automatic Number Plate Recognition for Australian Conditions
DICTA '05 Proceedings of the Digital Image Computing on Techniques and Applications
AdaBoost with SVM-based component classifiers
Engineering Applications of Artificial Intelligence
A configurable method for multi-style license plate recognition
Pattern Recognition
Vehicle number plate recognition using mathematical morphology and neural networks
WSEAS Transactions on Computers
Research and Realization of Improved Pattern Matching in License Plate Recognition
IITAW '08 Proceedings of the 2008 International Symposium on Intelligent Information Technology Application Workshops
A Method of Number-Plate Character Recognition Algorithm Based on Boosting Classification
CMC '09 Proceedings of the 2009 WRI International Conference on Communications and Mobile Computing - Volume 03
Automatic vehicle identification for Argentinean license plates using intelligent template matching
Pattern Recognition Letters
Hi-index | 0.00 |
The automatic number-plate recognition (ANPR) problem is attracting attention of many research scientists. However, there are not many researches focusing on building an ANPR system for smart-phones to recognize the motorcycles number plate dynamically on the street. In addition, the mobility and sensor rich of mobile device has not been much exploited. This paper introduces an innovative approach for building an ANPR software on Android smart-phones using neural network which can be applied to the mobile sensing to support intelligent traffic monitoring. Our approach is divided into two main parts: i) building an ANPR software on mobile phone using OpenCV and neural network; ii) evaluating the software on real traffic. The ANPR development includes three main steps: using AdaBoots classification method to locate the area which contains the number plate, applying morphology method to separate characters within the number plate, and using neural network for characters recognition. For evaluation the software, we take the location and speed of recognized number plate into account. This evaluation raises some research challenges in the area of building mobile ANPR software.