A New Hierarchical Architecture Based on SVM for Persian License Plate Character Recognition

Each license plate recognition system is composed of three main parts, namely,license plate detection, character segmentation and character recognition. In thispaper, we focus on the improvement and innovation of the character recognitionstep. For this purpose, a new hierarchical architecture based on Support VectorMachines (SVMs) is suggested for Persian license plate characters recognition.Clustering characters in the hierarchical architecture is proposed based on a newcriterion using a confusion matrix. The criterion and the confusion matrix have notbeen used for clustering in this way. The hierarchical architecture precision is97/4% and recognizes the entire characters of a license plate in approximately60ms. All evaluations and comparisons amiong the performances of previousmethods and the proposed method in this paper have been done in the samehardware and software test bed. The dataset obtained from images in realconditions such as, day, night, different distances and angles.

کلیدواژه ها:

License Plate Recognition ، Persian Character Recognition ، Hierarchical Architecture ، Support Vector Machine