Despite the evident practical importance of license plate recognition (LPR), corresponding research is limited by the volume of publicly available datasets due to privacy regulations such as the General Data Protection Regulation (GDPR). To address this challenge, synthetic data generation has emerged as a promising approach. In this paper, we propose to synthesize realistic license plates (LPs) using diffusion models, inspired by recent advances in image and video generation. In our experiments a diffusion model was successfully trained on a Ukrainian LP dataset, and 1000 synthetic images were generated for detailed analysis. Through manual classification and annotation of the generated images, we performed a thorough study of the model output, such as success rate, character distributions, and type of failures. Our contributions include experimental validation of the efficacy of diffusion models for LP synthesis, along with insights into the characteristics of the generated data. Furthermore, we have prepared a synthetic dataset consisting of 10,000 LP images, publicly available at https://zenodo.org/doi/10.5281/zenodo.13342102. Conducted experiments empirically confirm the usefulness of synthetic data for the LPR task. Despite the initial performance gap between the model trained with real and synthetic data, the expansion of the training data set with pseudolabeled synthetic data leads to an improvement in LPR accuracy by 3% compared to baseline.
A Robust Attentional Framework for License Plate Recognition in the Wild
Northwestern Polytechnical University（西北工业大学）；National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（空天地海一体化大数据应用技术国家工程实验室）；The University of Adelaide（阿德莱德大学）；Minsheng Fintech Corp. LTD（民生金融科技有限公司）
VRAE: Vertical Residual Autoencoder for License Plate Denoising and Deblurring
Ha Noi University of Science and Technology（河内科学技术大学）；Center of Environmental Intelligence（环境智能中心）；VinUniversity（文大学）；University of Southern California（南加州大学）
A New Hybrid Model of Generative Adversarial Network and You Only Look Once Algorithm for Automatic License-Plate Recognition
Electrical and Computer Engineering, Kharazmi University（卡扎尔米大学电气与计算机工程学院）；Faculty of Mathematics and Computer Science, University of Bremen（不莱梅大学数学与计算机科学学院）；School of Computing, University of the Fraser Valley（弗雷泽大学计算机学院）
Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；School of Computer Science, The University of Adelaide（阿德莱德大学计算机科学学院）
Advancing Multinational License Plate Recognition Through Synthetic and Real Data Fusion: A Comprehensive Evaluation
Pontifical Catholic University of Paraná (PUCPR), Curitiba, Brazil；Federal University of Paran\'a (UFPR), Curitiba, Brazil；Federal Institute of Paran\'a (IFPR), Irati, Brazil；Federal University of Ouro Preto (UFOP), Ouro Preto, Brazil；Federal University of Technology-Paran\' a (UTFPR), Curitiba, Brazil
Next-Generation Parallel Decoder for LPDR: Architectural Optimization and Class-Balanced GAN-Augmentation
School of Electrical Engineering；Computer Science National University of Sciences \& Technology Islamabad, Pakistan sobaid.mscs25seecs.edu.pk；Computer Science National University of Sciences \& Technology Islamabad, Pakistan nchandio.mscs25seecs.edu.pk；Computer Science National University of Sciences \& Technology Islamabad, Pakistan njamil.mscs25seecs.edu.pk；Computer Science National University of Sciences \& Technology Islamabad, Pakistan
Indian Commercial Truck License Plate Detection and Recognition for Weighbridge Automation
Ahmedabad University（艾哈迈达巴德大学）
检测和识别牌照是重要的自动化地磅服务。虽然许多大型数据库可用于拉丁文和中文字母数字车牌，但印度车牌的数据不足。特别是，印度商用卡车牌照数据库不足，尽管商用车牌照识别在物流管理和地磅自动化方面发挥着深远的作用。此外，识别车牌的模型由于其具有挑战性的性质，并且由于手写车牌的丰富频率，导致使用不同的字体样式，因此无法有效地概括这些数据。因此，识别和检测此类车牌的数据库和有效模型至关重要。本文提供了一个商用卡车牌照数据库，并在实时目标检测中使用最先进的模型：You Only Look Once Version 7和SceneText Recognition：置换自回归序列模型，我们的方法优于其他引用的参考文献，其中获得的最大精度小于90%，而我们在所提出的具有挑战性的车牌数据集上实现了95.82%的准确率。自动车牌识别，字符识别，车牌检测，视觉Transformer .
Performance Plateaus in Inference-Time Scaling for Text-to-Image Diffusion Without External Models
Interdisciplinary Program in Artificial Intelligence, Seoul National University（人工智能交叉学科项目，首尔国立大学）；Aerospace Engineering, Seoul National University（航空航天工程，首尔国立大学）；ASRI, AIIS, Seoul National University（ASRI、AIIS，首尔国立大学）
Vehicle and License Plate Recognition with Novel Dataset for Toll Collection
COMSATS University Islamabad（伊斯兰堡COMSATS大学）；Commonwealth Scientific and Industrial Research Organisation (CSIRO)（英联邦科学与工业研究组织（CSIRO））；Australian National University (ANU)（澳大利亚国立大学（ANU））；University of Technology Sydney (UTS)（悉尼科技大学（UTS））
我们提出了一个自动收费的框架，包括三个步骤：车型识别，车牌定位和阅读。然而，这三个步骤中的每一个都由于由几个因素引起的图像变化而变得不平凡。传统的汽车前部装饰会导致同类型汽车之间的差异。这些装饰物使车牌定位和识别困难，由于严重的背景杂波和部分遮挡。同样，在大多数车辆上，特别是卡车，车牌的位置也不一致。最后，对于车牌读取，不统一的字体样式、大小以及部分遮挡的字母和数字会引起变化。我们提出的框架利用了骨干深度学习架构的数据可用性和性能评估。我们收集了一个新的数据集，\emph{Diverse Vehicle and License Plates Dataset (DVLPD)}，包括10k图像属于六种车辆类型。然后，每个图像都被手动注释为车辆类型、车牌及其字符和数字。对于这三个任务中的每一个，我们评估了You Only Look Once（YOLO）v2、YOLOv3、YOLOv4和FasterRCNN。为了在Raspberry Pi上实时实现，我们评估了名为Tiny YOLOv3和Tiny YOLOv4的较轻版本的YOLO。YOLOv4在车型识别、车牌检测和车牌读取方面的最佳平均精度（mAP@0.5）分别为98.8%、98.5%和98.3%，而其较轻版本，即，Tiny YOLOv4在车型识别、车牌检测和车牌读取方面的mAP分别为97.1%、97.4%和93.7%。数据集和训练代码可在…
Mobile Phone Based Vehicle License Plate Recognition for Road Policing
TCS Innovation Labs - Mumbai（塔塔咨询服务公司孟买创新实验室）
一般来说，交通警察通过车辆牌照来识别车辆。车牌识别在智能交通管理系统中有着广泛的应用.全球的安全形势，特别是印度的安全形势，要求为交通警察配备一个系统，使他们能够即时获得车辆的详细信息。该系统应该易于使用，应该是移动的，并工作24 x 7。在本文中，我们描述了一个基于手机，客户端-服务器架构，车牌识别系统。虽然我们使用最先进的图像处理和模式识别算法调整为印度的条件，自动识别非统一的车牌，主要贡献是在创建一个端到端的可用的解决方案。客户端应用程序在移动终端上运行，并且可以访问车辆信息数据库的服务器应用程序被集中托管。该解决方案能够捕获由手机摄像头捕获的牌照图像并将其传递到服务器;在服务器上识别牌照号码;然后将与牌照相关联的数据立即发送回移动终端。我们详细描述了端到端的系统架构。该系统的工作原型已在实验室环境中实现。
TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition
Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University（水电工程智能视觉监测湖北省重点实验室，中国三峡大学）；College of Computer and Information Technology, China Three Gorges University（计算机与信息学院，中国三峡大学）；Hubei Key Laboratory of Digital Finance Innovation（数字金融创新湖北省重点实验室）；School of Information Engineering, Hubei University of Economics（信息工程学院，湖北经济学院）
A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot
Unmanned System Research Institute（无人系统研究院）；School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University（西北工业大学人工智能与光学电子学院（iOPEN））
