Real-Time Vehicle License Plate Recognition Using Deep Learning

摘要: A new cascade framework of real-time automated vehicle license plate recognition (VLPR) deep learning-based for intelligent transportation system applications in smart city is proposed. Our workflow includes two steps, which starts with localizing the image captured from cameras by using you look only once (YOLO)9000 and then recognizes whole car characters leveraging convolutional neural networks (CNNs) without segmentation. We also investigate that present effect kernel size, depth, width CNNs on performance. Even though these steps are trained separately, we joint them together testing images. The VLPR proposed not can display excellent performance even under bad condition, but be utilized deployed efficiently to GPU. In our experiments, 99.98% achieved Chinese test-time one 17.25 ms.