Car License Plate Recognition using Color Features of Persian License Plates

Car license plate recognition is addressed in this paper. Given the developmentof intelligent transportation systems, it is absolutely essential to implement a stronglicense plate recognition system. Efforts were made to put forward a novel reliablemethod for car license plate recognition in Iran. Each License plate recognitionsystem comprises three main parts. The first part is the license plate detection stage.The blue color feature of the license plate margin along with Scale-InvariantFeature Transform (SIFT) algorithm were used for this purpose, The accuracy ofthe presented method over the database was approximately 90% in less than asecond. License plate morphological features were utilized upon charactersegmentation. Using these features, areas with sizes close to that of the charactersof a license plate may be searched. The accuracy of this method was almost 95% Aprobabilistic neural network together with a Support Vector Machine (SVM) wasemployed at the character recognition stage. For this stage, an accuracy of nearly97% in 55 milliseconds for each license plate was achieved.

کلیدواژه ها:

License plate recognition ، SIFT ، SVM ، Intelligent transportation systems