The Research On Vehicles' License Plates Recognition System Based On Rough Set

The rough set can analyze and deal with vagueness, disaccord and uncertainty information, discover the connotative rule. The object of it is the information system. Vehicles' license plates (VLP) recognition system is a core technology in the intelligent traffic field. So the research on VLP recognition system based on rough set is very meaningful and practical. The following work is finished in this paper.1. Two VLP segmentation methods are presented in this paper. One is based on the edge detecting; another is based on the texture. All of them can segment plates from the image.2. Three inclination rectification methods are presented in this paper. They can rectify the long rim inclined, long and short rim inclined and distorted plates.3. The research on the discrimination, reduction, rule matching is carried out in this paper. The improved equidistance discrimination and rule matching are presented. They are good at anti-jamming.4. A rough set based method is presented for the car's plate characters recognition. The features of the training samples are extracted to build up the decision table. The rough set theory is applied to reduce the decision attributes of the table. Then the decision rules can be generated from the reduced decision table. The rule-match algorithm is based on the creditability of the rules. The application examples have showed a good recognition result on the car's plate characters. The reduced decision attributes can improve the generality of the rules and simplify the rule matching.5. The software of the VLP recognition system is made by using the Visual C++6.0.