Car License Plate Recognition (LPR) system has a broad application to the transportation management and the public security supervision. In this paper, a complete LPR system is addressed including the algorithm on the license plate character recognition. The plate recognition algorithm includes character segmentation and character recognition. This system completed character segmentation part using the similarity between a character string and license plate algorithm, and made corresponding improvement, and completed character recognition with wavelet transformation and support vector machine. Especially in the character recognition of license plate algorithm, this paper introduced Decision-tree based SVM method aiming at license plate characters to improve the recognition accuracy and shorten training time. Experimental results demonstrate that using this method to recognise the license plate characters can get a high recognition accuracy and speed. |