Design of a recognition system for special Malaysian car plates using stroke analysis

Abstract

Car-plate recognition systems are used commercially, both in the overseas and locally. In Malaysia, however, the usage of car-plate recognition systems is restricted to the ordinary car-plates. This means that the system is unable to detect car-plates assigned for taxis, as well as special types of car-plates. These special types of car-plates use special words to designate special occasions such as SUKOM, Putrajaya, Tiara, etc., instead of using the normal alphabets. Therefore, this system is aimed for implementation of a recognition system for Special Malaysian car plates using the recognition technique of Stroke Analysis. The system consists of several modules. The system is an offline system where the images gathered are first preprocessed using image processing techniques. Next, the image is converted into a binary image. After that, the boundary of the car plate characters is extracted. Then the image is passed through a stroke analysis system, i.e. the main module of the system. Here, the strokes for the characters are extracted and matched to a listed sequence. Finally, the system displays the output in ASCII format.