Research On License Plate Recognition Algorithm Based On Support Vector Machine (SVM)

With the continuous development of our country’s economy, the number of cars is constantly increasing, which leads to such situations as urban traffic jams, etc. License plate recognition system, which has been applied in highway traffic, high speed monitoring and safe parking lot, etc, has become an indispensable part of such areas as transport hubs and traffic safety etc. The upgrade of recognition rate and accuracy for license plate recognition system, is becoming increasingly important for modern transportation technology.License plate recognition system mainly includes image pre-processing, license plate location, character segmentation and character recognition etc. In this paper, such approaches as gray-scale transformation and top hat transform are used so that the post-processed license plate image can be protected from many interference factors and Sobel edge detection, mathematical morphology and structural elements plates are used to locate the license plates. In character segmentation part, the combination of vertical projection and license plate priori knowledge is used to segment the post-processed license plate character. In character recognition section, a character recognition approach based on kernel similar merge algorithm support vector machine(SVM) is proposed and overlapping coefficient is introduced, thus reducing the number of support vector machine(SVM) classifier, thereby increasing the recognition rate. In order to better demonstrate the effectiveness of the new approach, a license plate recognition system has been constructed and a lot of experiments have been conducted in this paper. The analysis of experimental data shows that the new recognition approach proposed in this paper can improve the recognition rate and accuracy of license plate recognition system to some extent.