Intelligent License Plate Recognition

Abstract

Road traffic accident is the leading cause of deaths and injuries in the world according to the World Health Organization (WHO). Every year many deaths and injuries are reported and most of them are in developing countries; the problem has great impact in Africa. Intelligent License Plate Recognition and reporting (ILPR) plays an important role in minimizing traffic accidents by implementing traffic monitoring and management systems. Since the number of vehicles are increasing, breaking traffic rules, entering restricted areas are becoming a trend. So, to control these actions, a system which can recognize vehicles by their License Plate (LP) is crucial. In this paper, we have developed ILPR system, which aims at reducing traffic accidents by processing an input image of a vehicle and reporting on its legality status. The ILPR starts with preprocessing and then extracts the LP using edge detection and vertical projection algorithms. To identify the License Plate Number (LPN), characters found on the LP are extracted and recognized by Artificial Neural Networks (ANN), which we trained with sample characters. If the recognized LPN is found to be a suspect after cross checking it with a pre-stored database, it will be sent to a person in charge via Short Message Service (SMS). In the recognition part, different papers use template matching, but is sensitive to noise. In order to mitigate the noise problem, our system uses ANN. We have also added SMS module. The system is implemented using MATLAB and Java.