A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector

  title={A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector},
  author={Rayson Laroca and Evair Severo and Luiz Antonio Zanlorensi and Luiz Oliveira and Gabriel Resende Gonçalves and William Robson Schwartz and D. Menotti},
  journal={2018 International Joint Conference on Neural Networks (IJCNN)},
Automatic License Plate Recognition (ALPR) has been a frequent topic of research due to many practical applications. [] Key Method The Convolutional Neural Networks (CNNs) are trained and finetuned for each ALPR stage so that they are robust under different conditions (e.g., variations in camera, lighting, and background). Specially for character segmentation and recognition, we design a two-stage approach employing simple data augmentation tricks such as inverted License Plates (LPs) and flipped characters…

Mobile Registration Number Plate Recognition Using Artificial Intelligence

Convolutional Neural Network (CNN) is trained and fine-tuned for the recognition stage to become more dynamic, plaint to diversification of backgrounds, producing better results than commercially available systems, PlateRecognizer and OpenALPR.

License Plate Detection and Recognition in Unconstrained Scenarios

The main contribution is the introduction of a novel Convolutional Neural Network capable of detecting and rectifying multiple distorted license plates in a single image, which are fed to an Optical Character Recognition (OCR) method to obtain the final result.

Rethinking and Designing a High-Performing Automatic License Plate Recognition Approach

The proposed VSNet outperforms state-of-the-art methods by more than 50% relative improvement on error rate, achieving >99% recognition accuracy on CCPD and AOLP datasets with 149 FPS inference speed and illustrates an outstanding generalization capability when evaluated on the unseen PKUData and CLPD datasets.

Vehicle Number Plate Detection and Categorization Using CNNs

This work proposes a proposed method to detect and recognize license plates in real-time that is particularly designed to work on videos captured by a camera, and it is a distinct approach that is composed of three main phases like plate detection, class letter segmentation, and recognition.

Recognizing License Plates in Real-Time

This work proposes a set of techniques to enable real-time and accurate license plate recognition, and implements a complete LPDR system that is not only among the most accurate ones but also the fastest, and can be easily applied to other scenarios.

Layout-invariant license plate detection and recognition

This work develops an effective system using deep convolutional neuron network (CNN) that can process LPs with different layouts, demonstrating promising accuracy and real-time CPU inference in comparison with the state-of-the-art approaches.

Synthesizing Large-Scale Datasets for License Plate Detection and Recognition in the Wild

This paper proposes to use a virtual world simulator to automatically generate realistic images with precise annotations, effectively avoiding the need for laborious image acquisition and labeling, and presents a DCNN based method for plate corner detection.

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

This work presents an efficient, robust and layout-independent ALPR system based on the YOLO object detector that contains a unified approach for license plate detection and layout classification and that leverages post-processing rules in the recognition stage to eliminate a major shortcoming of existing ALPR systems.

An Efficient CNN-based Approach for Automatic Brazilian License Plate Recognition

An ALPR system with an accuracy of 97.91% is built using approximately sixty-five thousand unlabeled images from the Federal Highway Police (PRF) captured by the institution’s radars, which outperform the most reliable studies for Brazilian license plates so far.



Benchmark for license plate character segmentation

A benchmark composed of a dataset designed to focus specifically on the character segmentation step of the ALPR within an evaluation protocol is proposed and an evaluation measure more suitable than the Jaccard coefficient regarding the location of the bounding box within the ground-truth annotation is proposed.

Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs

Inspired by the success of deep neural networks in various vision applications, DNNs are leveraged to learn high-level features in a cascade framework, which lead to improved performance on both detection and recognition.

Robust license plate detection in the wild

This work explores and customize state-of-the-art detection approaches for exclusively handling the LPD in the wild, namely YOLO (You-Only-Look-Once) and its variant YOLo-9000 (referred here as Y OLO-2), and customize them for effectively handling theLPD.

License Plate Detection and Recognition Using Deeply Learned Convolutional Neural Networks

This work details Sighthounds fully automated license plate detection and recognition system, built using a sequence of deep Convolutional Neural Networks interlaced with accurate and efficient algorithms.

Vehicle License Plate Recognition With Random Convolutional Networks

An OCR approach based on convolutional neural networks (CNNs) for feature extraction that can achieve recognition rates of over 98% for digits and 96% for letters, something that neither SVMs operating on image pixels nor CNNs trained via back-propagation can achieve.

Real-time automatic license plate recognition for CCTV forensic applications

A novel approach for efficient localization of license plates in video sequence and the use of a revised version of an existing technique for tracking and recognition is proposed, intelligent enough to automatically adjust for varying camera distances and diverse lighting conditions.

A Robust and Efficient Approach to License Plate Detection

This paper presents a robust and efficient method for license plate detection with the purpose of accurately localizing vehicle license plates from complex scenes in real time and substantially outperforms state-of-the-art methods in terms of both detection accuracy and run-time efficiency.

Segmentation- and Annotation-Free License Plate Recognition With Deep Localization and Failure Identification

A new ALPR workflow is proposed that includes novel methods for segmentation- and annotation-free ALPR, as well as improved plate localization and automation for failure identification, and the performance gap due to differences between training and target domain distributions is minimized using an unsupervised domain adaptation.

Automatic License Plate Recognition (ALPR): A State-of-the-Art Review

This paper categorizes different ALPR techniques according to the features they used for each stage, and compares them in terms of pros, cons, recognition accuracy, and processing speed.

Vehicle license plate detection using region-based convolutional neural networks

The state-of-the-art object detection techniques, including convolutional neural networks with region proposal, its successors, and the exemplar-SVM are used in this work to provide solutions to the problem.