Robust license plate recognition using neural networks trained on synthetic images. (September 2019)

• Record Type: Journal Article
• Authors: Björklund, Tomas; Fiandrotti, Attilio; Annarumma, Mauro; Francini, Gianluca; Magli, Enrico
• Is Part Of: Pattern recognition. Volume 93(2019:Sep.)
• Page Start: 134
• Page End: 146
• Publication Date: 2019-09
• Subjects: License plate recognition (LPR) -- Convolutional neural network (CNN) -- Synthetic training; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.04.007
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A complete vehicle license plate reading system is proposed. CNNs trained for LPR on only synthetic samples generalizes well to real images. A re-classification of fully convolutional classifications improves performance. Results on other datasets shows an improvement over previous LPR systems. Graphical abstract: Abstract: In this work, we describe a License Plate Recognition (LPR) system designed around convolutional neural networks (CNNs) trained on synthetic images to avoid collecting and annotating the thousands of images required to train a CNN. First, we propose a framework for generating synthetic license plate images, accounting for the key variables required to model the wide range of conditions affecting the aspect of real plates. Then, we describe a modular LPR system designed around two CNNs for plate and character detection enjoying common training procedures and train the CNNs and experiment on three different datasets of real plate images collected from different countries. Our synthetically trained system outperforms multiple competing systems trained on real images, showing that synthetic images are effective at training a CNNs for LPR if the training images have sufficient variance of the key variables controlling the plate aspect.