Vehicle style recognition based on image processing and neural network

Abstract

A vehicle style recognition method using computer vision, image processing and RBF neural network is presented in the paper. First, a vehicle side image is acquired by using a high-speed vidicon. Then a vehicle edge outline image was obtained by a series of image processing and the vehicle features are extracted from the edge outline image. Finally, the vehicle is recognized and classified using a RBF neural network. Experimental results show that the proposed method has a good classification effect in the practical application of vehicle style recognition at vehicle toll stations. © 2012 Springer-Verlag GmbH.