Improving Robustness of License Plates Automatic Recognition in Natural Scenes

Fan, Xudong; Zhao, Wei

doi:10.1109/tits.2022.3151475

Cited by 33 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) Method based on DL technology The LPR techniques that relied on visual features have run into development roadblocks because of a variety of issues, including complex settings and erratic image lighting. DL performs exceptionally well at detecting objects [14]. The multi-OD algorithm has significantly outperformed earlier systems.…”

Section: License Plate Detection Algorithmmentioning

confidence: 91%

A Light Vehicle License-Plate-Recognition System Based on Hybrid Edge–Cloud Computing

Leng,

Chen,

Zhao

et al. 2023

Sensors

View full text Add to dashboard Cite

With the world moving towards low-carbon and environmentally friendly development, the rapid growth of new-energy vehicles is evident. The utilization of deep-learning-based license-plate-recognition (LPR) algorithms has become widespread. However, existing LPR systems have difficulty achieving timely, effective, and energy-saving recognition due to their inherent limitations such as high latency and energy consumption. An innovative Edge–LPR system that leverages edge computing and lightweight network models is proposed in this paper. With the help of this technology, the excessive reliance on the computational capacity and the uneven implementation of resources of cloud computing can be successfully mitigated. The system is specifically a simple LPR. Channel pruning was used to reconstruct the backbone layer, reduce the network model parameters, and effectively reduce the GPU resource consumption. By utilizing the computing resources of the Intel second-generation computing stick, the network models were deployed on edge gateways to detect license plates directly. The reliability and effectiveness of the Edge–LPR system were validated through the experimental analysis of the CCPD standard dataset and real-time monitoring dataset from charging stations. The experimental results from the CCPD common dataset demonstrated that the network’s total number of parameters was only 0.606 MB, with an impressive accuracy rate of 97%.

show abstract

Section: License Plate Detection Algorithmmentioning

confidence: 91%

A Light Vehicle License-Plate-Recognition System Based on Hybrid Edge–Cloud Computing

Leng,

Chen,

Zhao

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The authors proposed a novel End-to-end Irregular License Plate Recognition (EILPR) to work out the detection and recognition of LP of multiline text or arbitrary shooting angles [10]. The special part of this method is that it combines LP detection and recognition into an overall structure, which is much more different from the traditional Two-stage method.…”

Section: Automatic Perspective Alignmentmentioning

confidence: 99%

Artificial intelligence technology in license plate recognition

Huang

2023

ACE

View full text Add to dashboard Cite

Due to the importance of license plate recognition in many parts in human society, several methods are concluded and proposed in this article. In this work, artificial intelligence (AI) technology, deep learning, and neural networks are put into use in different aspects or modules of license plate recognition methods. Current methods can be divided into two categories, one is the traditional methods and the other is method using AI technology. Two-stage method is a typical example for traditional methods. In this work, other methods such as RT-LPDRnet method, which takes YOLO v5 into use, is an example for AI technology in license plate recognition. Now commercial license plate recognition generally adopts the method of end-to-end deep learning, while some methods of character segmentation first and then recognition are still worthy of study. In this work, three evaluation metrics are concluded to help evaluate the performance of previous methods. In addition, application of license plate recognition is proposed such as recognition in the parking lots, entrances and exits of expressway and electronic police system.

show abstract

“…Fan et al. [4] proposed a robust license plate detection network, together with a segmentation‐free network for the recognition of license plate characters, with better accuracy. Xiao et al.…”

Section: Related Workmentioning

confidence: 99%

“…Henry et al [14] presented a deep ALPR system for multinational ALPR. Fan et al [4] proposed a robust license plate detection network, together with a segmentation-free network for the recognition of license plate characters, with better accuracy. Xiao et al [15] introduced the automatic rectification scheme to ALPR.…”

Section: Two-stage License Plate Detection and Recognitionmentioning

confidence: 99%

“…Automatic License Plate detection and Recognition (ALPR) plays a critical role in intelligent transportation systems. It can find applications in many real-world problems including traffic monitoring [1], electronic toll collection [2] (ETC), intelligent parking lots [3] (IPLs), and elsewhere [4,5]. Due to its prominence and importance, ALPR has attracted great attention over the last two decades (see [6,7] for extensive surveys).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

FAFEnet: A fast and accurate model for automatic license plate detection and recognition

Zhou

Cheng

Jiang

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Automatic License Plate detection and Recognition (ALPR) is a key problem in intelligent transportation systems with wide applications in traffic monitoring, electronic toll collection (ETC), intelligent parking lots (IPLs), and elsewhere. Although numerous methods have been proposed in the literature, it is still challenging to strike a good balance between the accuracy and efficiency of ALPR. In this paper, a novel end-to-end CNN-based model is proposed, called Fast and Accurate Network with Feature Enhancement (FAFEnet), to jointly detect the license plates and recognize the characters with high accuracy and efficiency. Specifically, the FAFEnet model seamlessly integrates two CNN-based models, namely the detection and recognition modules, into a unified framework to reduce accumulated errors and computational overheads in two separate steps. The detection module is a lightweight model with only seven convolutional layers yet achieves over 99.8% accuracy rates for license plate detection across all datasets. The recognition module utilizes two feature enhancement blocks to compensate and enhance the shallow character features extracted by the detection module. Furthermore, the joint optimization of detection and recognition modules exploits the feature association in two modules, and thus improves the prediction accuracy while reducing the execution time. Finally, extensive experimental results on several real-world datasets demonstrate that FAFEnet outperforms all the competitors in terms of both accuracy and efficiency.

show abstract

Improving Robustness of License Plates Automatic Recognition in Natural Scenes

Cited by 33 publications

References 30 publications

A Light Vehicle License-Plate-Recognition System Based on Hybrid Edge–Cloud Computing

A Light Vehicle License-Plate-Recognition System Based on Hybrid Edge–Cloud Computing

Artificial intelligence technology in license plate recognition

FAFEnet: A fast and accurate model for automatic license plate detection and recognition

Contact Info

Product

Resources

About