Application of Extreme Learning Machine to Automatic License Plate Recognition

This paper proposes a new method for vehicle license plate recognition on the basis of Extreme Learning Machine ELM is a new category of neural networks which possesses compelling characteristics essential for license plate recognition, such as low computational complexity, fast training, and good generalization (as opposed to traditional neural networks). The proposed method studies incorporation of three ELMs (i.e, basic ELM, incremental ELM, and enhanced incremental ELM) into a typical pipeline for automatic license plate recognition. In the preliminary study (under Windows PC with MATLAB), the success rate of recognition is 875% with execution time of 0.3s. A comparative study also shows that the proposed method outperforms conventional approaches (template matching, edge statistics, RBI; and SVM) in terms of accuracy and speed.