Malaysia’s Car Plate Recognition System

Wee, Ming Qiu (2016) Malaysia’s Car Plate Recognition System. Final Year Project (Bachelor), Tunku Abdul Rahman University College.

Text Wee Ming Qiu_FULL TEXT.pdf Restricted to Registered users only Download (2MB)

Abstract

Malaysia’s car plate recognition system is explicitly developed to recognize the Malaysia’s car plate numbers with minimal human assistance. The main objective of the proposed system is to automatically recognize the car’s license plates and transform them in a computer understandable form with the implementation of the latest computer vision technology. The proposed system can be extended to serve multiple purposes such as record the car entry time, record the leaving times, calculate the parking payment, charge the bill according to car plate and so on. The proposed system is intended to minimize the human interaction and simplify the process required throughout the parking process. In order to achieve such mentioned functionalities without compromise the quality, the proposed system will be decomposed into four distinct modules, which are pre-processing, car plate localization, character segmentation and optical character recognition. However, the focus of this project will be concentrated on the car plate localization. The main objective of the car plate localization module is to localize the car plate, which means find the location of the car plate in an image. In current market, the existing car plate localization algorithms do not work very well in Malaysia’s car plate as the generated results are not compromising and satisfying. Therefore, a customized Malaysia’s car plate localization algorithm will be proposed in this project, to overcome the issues of low accuracy and efficiency