Comparison between Techniques in Feature Extraction

Abstract

The aim of this study is to develop a prototype of a Car Plate Recognition System using image processing technique in which it locates and recognizes car plates. The Road Transport Department of Malaysia has endorsed a specification for car plates which includes the font and size of characters that needs to be followed by car owners. However, there are cases where this specification is not being followed. This will cause problems in the recognition phase because the existing system will find difficulty in recognizing characters in car plates. To ensure the recognition can be done correctly, the feature extraction phase should be done successfully by applying appropriate technique. Therefore, this research is mainly focused on car plate feature extraction where an experiments using the feature extraction and template matching techniques were conducted. After that, a comparison will be done by using the results of the experiments. The result will be discussed and the techniques are compared at the end of this paper