Multi-Scale Regional Attention InfoGAN License Plate Recognition Network

XU Shengjun; DU Miao; DUAN Zhongxing; LI Minghai; HAN Jiuqiang

doi:10.7652/xjtuxb202308020

您当前的位置：

首页 >

文章列表页 >

Multi-Scale Regional Attention InfoGAN License Plate Recognition Network

更新时间：2025-05-08

- Multi-Scale Regional Attention InfoGAN License Plate Recognition Network
- Vol. 57, Issue 8, Pages: 206-218(2023)
- 作者机构：
  
  1. 西安建筑科技大学信息与控制工程学院,西安,710055
  2. 西安市建筑制造智动化技术重点实验室,西安,710055
  3. 西安交通大学电子与信息学部,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202308020
  CLC： TP391
- Online First：10 August 2023，
  
  Published：2023
- 稿件说明：
移动端阅览
XU Shengjun, DU Miao, DUAN Zhongxing, et al. Multi-Scale Regional Attention InfoGAN License Plate Recognition Network[J]. 2023, 57(8): 206-218.
DOI：

XU Shengjun, DU Miao, DUAN Zhongxing, et al. Multi-Scale Regional Attention InfoGAN License Plate Recognition Network[J]. 2023, 57(8): 206-218. DOI： 10.7652/xjtuxb202308020.

摘要

针对车牌图像倾斜、遮挡、失真、模糊导致车牌图像难以识别的问题

提出一种多尺度区域注意力InfoGAN车牌识别网络。基于InfoGAN框架提出一种多尺度区域注意力车牌超分辨率模块

通过引入颜色分布、字符结构特征的互信息约束

提升网络不同特征维度上的判别能力

重构失真、模糊的低分辨率车牌图像中的关键字符特征; 在无车牌字符位置标签信息的情况下

使用多尺度区域注意力机制对车牌全局特征图中的车牌字符和背景解耦合

渐进式地对不同尺度特征图进行不同区域加权

提高网络对字符区域显著性的关注能力和背景噪声区域的抗干扰能力; 提出多尺度语义车牌字符特征提取模块

对重构后车牌图像中字符特征解码并识别。在自建XAUAT-Parking数据集和公开CCPD数据集上进行车牌识别准确率实验

实验结果表明:所提网络在CCPD公开车牌数据集上的平均识别准确率为99.3%

在自建XAUAT-Parking数据集上的平均识别准确率为99.2%。所提网络在复杂场景下具有准确的车牌识别效果和较强的鲁棒性。

Abstract

A multi-scale regional attention InfoGAN license plate recognition network is proposed for difficult recognition of license plate images that are skewed

obscured

distorted

or blurred. First

a multi-scale regional attention license plate super-resolution module is proposed based on the InfoGAN framework. Mutual information constraints on color distribution and character structure features are introduced to improve the network's discriminant performance in different feature dimensions. Key character features in distorted and blurred low-resolution license plate images are reconstructed. Second

in the absence of the location label information of license plate characters

the license plate characters and background in the global feature map are decoupled by a multi-scale region attention mechanism to progressively weight different regions of the feature map at different scales

improving the network's performance to focus on the saliency of character regions and resist the interference of background noise regions. Finally

a multi-scale semantic license plate character extraction module is proposed to decode and recognize the character features in the reconstructed license plate image. Both the self-built XAUAT-Parking dataset and the publicly available CCPD dataset are used for license plate recognition accuracy experiments. The experimental results show that the proposed network has an average recognition rate of 99.3% for the CCPD dataset and of 99.2% for the self-built dataset. The research results show that the network features accurate license plate recognition and great robustness in complex scenes.

关键词

Keywords

references

GOU Chao, WANG Kunfeng, YAO Yanjie, et al. Vehicle license plate recognition based on extremal regions and restricted Boltzmann machines [J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(4): 1096-1107.

HOU Yongshun, QIN Xunhui, ZHOU Xiangdong, et al. License plate character segmentation based on stroke width transform [C]//2015 8th International Congress on Image and Signal Processing(CISP). Piscataway, NJ, USA: IEEE, 2015: 954-958.

HSU G S, CHEN J C, CHUNG Y Z. Application-oriented license plate recognition [J]. IEEE Transactions on Vehicular Technology, 2013, 62(2): 552-561.

NAVASTARA D A, MUSYAFIRA N, FATICHAH C, et al. Video-based license plate recognition using single shot detector and recurrent neural network [C]//2021 13th International Conference on Information Communication Technology and System(ICTS). Piscataway, NJ, USA: IEEE, 2021: 151-154.

TU Chunling, DU Shengzhi. A hierarchical RCNN for vehicle and vehicle license plate detection and recognition [J]. International Journal of Electrical and Computer Engineering, 2022, 12(1): 731-737.

LI Hui, WANG Peng, YOU Mingyu, et al. Reading car license plates using deep neural networks [J]. Image and Vision Computing, 2018, 72: 14-23.

LEE C Y, OSINDERO S. Recursive recurrent nets with attention modeling for OCR in the wild [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2016: 2231-2239.

ZHERZDEV S, GRUZDEV A. LPRNet: license plate recognition via deep neural networks [EB/OL]. [2022-10-01]. https://arxiv.org/abs/1806.10447.

QIN Shuxin, LIU Sijiang. Towards end-to-end car license plate location and recognition in unconstrained scenarios [J]. Neural Computing and Applications, 2022, 34(24): 21551-21566.

穆世义, 徐树公. 基于单字符注意力的全品类鲁棒车牌识别 [J]. 自动化学报, 2023, 49(1): 122-134.

MU Shiyi, XU Shugong. Full-category robust license plate recognition based on character attention [J]. Acta Automatica Sinica, 2023, 49(1): 122-134.

XU Hui, GUO Zhaohong, WANG Dahan, et al.2D license plate recognition based on automatic perspective rectification [C]//2020 25th International Conference on Pattern Recognition(ICPR). Piscataway, NJ, USA: IEEE, 2021: 202-208.

DONG Chao, LOY C C, HE Kaiming, et al. Image super-resolution using deep convolutional networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307.

LIU Wu, LIU Xinchen, MA H, et al. Beyond human-level license plate super-resolution with progressive vehicle search and domain priori GAN [C]//Proceedings of the 25th ACM international conference on Multimedia. New York, NY, USA: Association for Computing Machinery, 2017: 1618-1626.

LEE Seyun, KIM J H, HEO J P. Super-resolution of license plate images via character-based perceptual loss [C]//2020 IEEE International Conference on Big Data and Smart Computing(BigComp). Piscataway, NJ, USA: IEEE, 2020: 560-563.

ZHANG Minghui, LIU Wu, MA Huadong. Joint license plate super-resolution and recognition in one multi-task gan framework [C]//2018 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP). Piscataway, NJ, USA: IEEE, 2018: 1443-1447.

HAMDI A, CHAN Y K, KOO V C. A new image enhancement and super resolution technique for license plate recognition [J]. Heliyon, 2021, 7(11): e08341.

MIN D, LIM H, GWAK J. Improved method of license plate detection and recognition facilitated by fast super-resolution GAN [J]. Smart Media Journal, 2020, 9(4): 134-143.

HUANG Chien, LI Y H, ASLAM M S, et al. Super-resolution generative adversarial network based on the dual dimension attention mechanism for biometric image super-resolution [J]. Sensors, 2021, 21(23): 7817.

徐胜军, 邓博文, 史亚, 等. 一种编解码结构的车牌图像超分辨率网络 [J]. 西安交通大学学报, 2022, 56(10): 101-110.

XU Shengjun, DENG Bowen, SHI Ya, et al. An encoder-decoder-based super resolution network for license plate images [J]. Journal of Xi'an Jiaotong University, 2022, 56(10): 101-110.

CHEN Xi, DUAN Yan, HOUTHOOFT R, et al. InfoGAN: interpretable representation learning by information maximizing generative adversarial nets [C]//Advances in Neural Information Processing Systems 29(NIPS 2016). Vancouver, Canada: NIPS, 2016: 2180-2188.

XU Zhenbo, YANG Wei, MENG A, et al. Towards End-to-End license plate detection and recognition: a large dataset and baseline [C]//ECCV 2018. Cham, Germany: Springer International Publishing, 2018: 261-277.

LEDIG C, THEIS L, HUSZÁR F, et al. Photo-realistic single image Super-Resolution using a generative adversarial network [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2017: 105-114.

KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2016: 1646-1654.

PENG Xi, FERIS R S, WANG Xiaoyu, et al. RED-net: a recurrent encoder-decoder network for video-based face alignment [J]. International Journal of Computer Vision, 2018, 126(10): 1103-1119.[25] ZHANG Linjiang, WANG Peng, LI Hui, et al. A robust attentional framework for license plate recognition in the wild [J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(11): 6967-6976.

REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.

LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector [C]//Computer Vision-ECCV 2016. Cham, Germany: Springer International Publishing, 2016: 21-37.

LUO Canjie, JIN Lianwen, SUN Zenghui. MORAN: a multi-object rectified attention network for scene text recognition [J]. Pattern Recognition, 2019, 90: 109-118.

ZOU Yongjie, ZHANG Yongjun, YAN Jun, et al. A robust license plate recognition model based on Bi-LSTM [J]. IEEE Access, 2020, 8: 211630-211641.

WANG Tianwei, ZHU Yuanzhi, JIN Lianwen, et al. Decoupled attention network for text recognition [C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, CA, USA: AAAI Press, 2020: 12216-12224.

SEO T M, KANG D J. A robust layout-independent license plate detection and recognition model based on attention method [J]. IEEE Access, 2022, 10: 57427-57436.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multimodal Neural Network-Based Temperature Prediction Method for Lithium-Ion Batteries Under Mechanical Abuse Scenarios

Research on Entity Relation Extraction Method Based on Relational Prompts with Single-Module Single-Step Approach

Cross-Component Prediction for H.266/Versatile Video Coding Based on Lightweight Convolutional Neural Network

Image Super Resolution Algorithm Based on Receptive Field Optimization and Progressive Feature Fusion

Polarization Image Super-Resolution Reconstruction Network Using Contextual Dual Self-Correlation Attention

Related Author

HUANG Xinrong

QIN Zhengpeng

LI Qian

LI Jie

LIU Hui

ZHANG Zhi

WANG Qiyuan

ZOU Chengyi

Related Institution

School of Energy and Electrical Engineering, Chang'an University

College of Electronic Engineering, National University of Defense Technology

School of Computer Science and Technology, Harbin Institute of Technology

School of Engineering, Royal Melbourne Institute of Technology

School of Electronic and Information, Northwestern Polytechnical University

⁰