Fine-grained traffic checkpoint motor vehicle recognition system based on deep convolutional neural network

Deep convolutional neural network has been used extensively in the field of image recognition, in recent years. It is found that the recognition accuracy and efficiency greatly surpass that of the traditional algorithms. In this paper, we proposed a way to solve the problem of fine-grained motor vehicle recognition in traffic checkpoint using deep convolutional neural network. After being tested on the data set constructed by us, the result shows that the recognition accuracy and efficiency have been greatly improved, which means this approach have the potential to be used in practical applications.