An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detector

This paper presents an efficient and layout-independent Automatic License Plate Recognition (ALPR) system based on the state-of-the-art YOLO object detector that contains a unified approach for license plate (LP) detection and layout classification to improve the recognition results using post-processing rules. The system is conceived by evaluating and optimizing different models, aiming at achieving the best speed/accuracy trade-off at each stage. The networks are trained using images from several datasets, with the addition of various data augmentation techniques, so that they are robust under different conditions. The proposed system achieved an average end-to-end recognition rate of 96.9% across eight public datasets (from five different regions) used in the experiments, outperforming both previous works and commercial systems in the ChineseLP, OpenALPR-EU, SSIG-SegPlate and UFPR-ALPR datasets. In the other datasets, the proposed approach achieved competitive results to those attained by the baselines. Our system also achieved impressive frames per second (FPS) rates on a high-end GPU, being able to perform in real time even when there are four vehicles in the scene. An additional contribution is that we manually labeled 38,351 bounding boxes on 6,239 images from public datasets and made the annotations publicly available to the research community.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
License Plate Recognition AOLP YOLOv2 + Fast-YOLOv2 + CR-NET Rank-1 Recognition Rate 99.2 # 1
License Plate Recognition Caltech Cars YOLOv2 + Fast-YOLOv2 + CR-NET Rank-1 Recognition Rate 98.7 # 1
License Plate Recognition ChineseLP YOLOv2 + Fast-YOLOv2 + CR-NET Rank-1 Recognition Rate 97.5 # 1
License Plate Recognition EnglishLP YOLOv2 + Fast-YOLOv2 + CR-NET Rank-1 Recognition Rate 95.7 # 1
License Plate Recognition OpenALPR-EU YOLOv2 + Fast-YOLOv2 + CR-NET Rank-1 Recognition Rate 97.8 # 1
License Plate Recognition SSIG-SegPlate YOLOv2 + Fast-YOLOv2 + CR-NET Rank-1 Recognition Rate 98.2 # 1
License Plate Recognition UCSD-Stills YOLOv2 + Fast-YOLOv2 + CR-NET Rank-1 Recognition Rate 98 # 1
License Plate Recognition UFPR-ALPR YOLOv2 + Fast-YOLOv2 + CR-NET Rank-1 Recognition Rate 90 # 2

Methods