An efficient license plate character recognition algorithm based on shape context

It is usually hard for traditional machine-learning-based classification algorithms such as Support Vector Machine (SVM) to classify similar characters in the process of license plate character recognition. In this paper, we introduced an efficient character recognition system based on a local, robust shape descriptor called the shape context to solve this problem. We also improved the matching strategy overcome shape context’s slow running speed. Experiment result shows the proposed algorithm has higher accuracy and quicker running speed compare to traditional machine- learning-based algorithms.