A Method of Number-Plate Character Recognition Algorithm Based on Boosting Classification

A method of number-plate characters recognition using AdaBoost algorithm, which based on template matching is presented in order to improve recognition rate and reduce recognition time. The method is divided into two stages. In the first stage, classifier is trained by template matching which is improved through AdaBoost classification, at the same time, classification rules are found. Number-plate characters are recognized by classification rules and then classification results are obtained in the second stage. The experiment results have showed that, for a vehicle number-plate, recognition rate of characters is more than 90% and the recognition time of characters is less than 2 second by using the method.