Enhancing Thinning Method for Malaysian Car Plates Recognition

The Road Transport Department of Malaysia has endorsed a specification for car plates that includes the font and size of characters that must be followed by car owners. However, there are cases where this specification is not followed. This will cause problems in the recognition phase because the existing systems will find difficulty in recognizing characters in car plates. To ensure the recognition can be done correctly, the thinning and feature extraction phases should be done successfully by applying appropriate techniques. Inappropriate technique applied during thinning phase can cause wrong value derived during the feature extraction phase that use statistical method and thus affected the process of car plate recognition. Therefore, this paper is mainly focused on the thinning process of car plate images where a suitable technique was applied. This technique will produce a successful thin line of characters with a standard size regardless of its various sizes and font types. This standard size then was used as a template to derive a value for each character during feature extraction phase and will be very useful in recognition phase. This paper provided with an analytical overview of the proposed technique and the expected detail outcome for this research.