CNN-applications in toll driving

This paper describes a system for the automatic identification of vehicles by the contents of its license plate. The system has been developed over th e last five years and is one of the four candidate systems for automatic to ll collection in the Netherlands. Due to the extreme time and performance r equirements placed on the system, advanced techniques like DT-CNNs and clas sifier combining are used. The first tests on the road show that the system correctly recognizes 85.4% of the passing vehicles, while marking the rema ining 14.6% as unrecognizable.