research-article

Application of Improved LeNet-5 Network in Traffic Sign Recognition

Authors:

Wei CuiAuthors Info & Claims

ICVIP '19: Proceedings of the 3rd International Conference on Video and Image Processing

Pages 13 - 18

https://doi.org/10.1145/3376067.3376102

Published: 25 February 2020 Publication History

Get Access

Abstract

Considering that most convolutional neural network (CNN) models designed for traffic sign recognition (TSR) have sacrificed more resources and complicated network model development while pursuing higher performance, LeNet-5 shallow CNN with low complexity has been selected for improvement. Increasing the number of convolution kernel in the first convolution layer (C1 layer) and the third convolution layer (C3 layer) while reducing the size of the convolution kernel in C3 layer. Introducing Rectified Linear Unit (ReLU) function with better performance. The maximum pooling is introduced instead of mean pooling. Besides, the output layer employs support vector machine (SVM) to shorten the operation time. The research results demonstrate that the improved LeNet-5 network has an identification accuracy rate of 98.12% and the identification time is 0.154s for traffic signs in German Traffic Sign Recognition Benchmark (GTSRB), which could guarantee the real-time performance of the system and effectively reduce the complexity of the system on the basis of a high recognition rate.

References

[1]

BY. Liu, DY. Jia, KJ Lu, et al., 2017, Infrastructure-Assisted Message Dissemination for Supporting Heterogeneous Driving Patterns, IEEE Trans. on Inte. Trans. Syst., 18(10), (Oct. 2017), 2865--2876. DOI= 10.1109/TITS.2017.2661962

Digital Library

Google Scholar

[2]

G. Hong, B. Kim, D. Dogra, P. Roy, 2018, A Survey of Real-time Road Detection Techniques Using Visual Color Sensor, Journal of Multimedia Information System (KMMS), 5 (1), (May, 2018), 9--14, DOI= 10.9717/JMIS.2018.5.1.9

Crossref

Google Scholar

[3]

B. Kim, G. Hong, J. Kim, Y. Choi, An Efficient Vision-based Object Detection and Tracking using Online Learning, Journal of Multimedia Information System (KMMS), 4 (4), (Dec. 2017), 285--288, DOI= 10.9717/JMIS.2017.4.4.285

Crossref

Google Scholar

[4]

Z. Zhou, Z. Shi, Y. Guo, et al. 2019, Object Detection in 20 Years: A Survey, arXiv:1905.05055 [cs.CV], (May, 2019). This work has been submitted to the IEEE TPAMI for possible publication.

Google Scholar

[5]

Zhu Y, Liao M, Yang M, et al., 2018, Cascaded Segmentation-Detection Networks for Text Based Traffic Sign Detection, IEEE Trans. on Inte. Trans. Syst., (Jan. 2018), 19(1), 209--219. DOI= 10.1109/TITS.2017.2768827

Crossref

Google Scholar

[6]

T. Surinwarangkoon, S. Nitsuwat, and E. Moore, 2013, Traffic Sign Recognition System for Roadside Images in Poor Condition. International Journal of Machine Learning and Computing, (3) 1 (Feb. 2013) 121--126. DOI= 10.7763/IJMLC.2013.V3.285

Crossref

Google Scholar

[7]

S. Karungaru, H. Nakano, and M. Fukumi, 2013, Road Traffic Signs Recognition Using Genetic Algorithms and Neural Networks. International Journal of Machine Learning and Computing, (Jun. 2013), 3 (3) 313--317 DOI= 10.7763/IJMLC.2013.V3.329

Crossref

Google Scholar

[8]

H. Luo, Y. Yang, et al., 2018, Traffic Sign Recognition Using a Multi-Task Convolutional Neural Network, IEEE Trans. on Inte. Trans. Syst., 19 (4), (Apr. 2018), 1100--1111. DOI=10.1109/TITS.2017.2714691

Crossref

Google Scholar

[9]

J. Zhang, Q. Huang, H. Wu and Y. Liu., 2017, A Shallow Network with Combined Pooling for Fast Traffic Sign Recognition, information, (Apr., 2017), 8 (45). DOI= 10.3390/info8020045

Crossref

Google Scholar

[10]

Lecun Y L, Bottou L, Bengio Y, et al., 1998, Gradient-Based Learning Applied to Document Recognition. In Proceedings of the IEEE, 86 (11) (Nov. 1998), 2278--2324. DOI=10.1109/5.726791

Crossref

Google Scholar

[11]

S. Ji, W. Xu, et al., 2013, 3D convolutional neural networks for automatic human action recognition. United States Patent, Pantent No. USOO8345984B2. (Jan. 2013).

Google Scholar

[12]

Zeng Y, Xu X, Fang Y, et al., Traffic Sign Recognition Using Deep Convolutional Networks and Extreme Learning Machine, In International Conference on Intelligent Science and Big Data Engineering, (Suzhou, China, 14-16 June, 2015), 9242, 272--280. DOI=10.1007/978-3-319-23989-7_28

Crossref

Google Scholar

[13]

Y. Chen, F. Zhang, 2018, Research on traffic sign recognition method based on cross entropy, Software Guide, (Apr. 2018), 17 (12), 24--28. DOI=10.11907/rjdk.181542

Crossref

Google Scholar

Cited By

View all

Qiu LRahman ADolah MGe S(2024)The Research on the Application of Artificial Intelligence in Visual Art- based on Souvenir DesignWSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS10.37394/23209.2024.21.621(55-64)Online publication date: 14-Feb-2024
https://doi.org/10.37394/23209.2024.21.6
Guo KWu ZWang WRen SZhou XGadekallu TLuo ELiu C(2024)GRTR: Gradient Rebalanced Traffic Sign Recognition for Autonomous VehiclesIEEE Transactions on Automation Science and Engineering10.1109/TASE.2023.327020221:3(2349-2361)Online publication date: Jul-2024
https://doi.org/10.1109/TASE.2023.3270202
Zhou FZu HLi YSong YLiao JZheng C(2023)Traffic-Sign-Detection Algorithm Based on SK-EVC-YOLOMathematics10.3390/math1118387311:18(3873)Online publication date: 11-Sep-2023
https://doi.org/10.3390/math11183873
Show More Cited By

Index Terms

Application of Improved LeNet-5 Network in Traffic Sign Recognition
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Object recognition

Recommendations

Two-Stage Traffic Sign Classification System
Abstract
Traffic Sign Recognition (TSR) has received widespread attention due to increased traffic accidents caused by a failure to recognize road traffic signs. Most Traffic Sign Recognition remains challenging due to the illumination of natural scenes, ...
Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5
Convolutional neural network (CNN) is a very important method in deep learning, which solves many complex pattern recognition problems. Fruitful results have been achieved in image recognition, speech recognition, and natural language processing. Compared ...
Digital Recognition Based on Improved LENET Convolution Neural Network
ICMLT '18: Proceedings of the 2018 International Conference on Machine Learning Technologies

To promote the performance of LeNet-5 convolutional neural network, an improved LeNet-5 convolutional neural network was proposed. The improved neural network model was trained using MNIST character library. The effects on the performance of final ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

ICVIP '19: Proceedings of the 3rd International Conference on Video and Image Processing

December 2019

270 pages

ISBN:9781450376822

DOI:10.1145/3376067

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Shanghai Jiao Tong University: Shanghai Jiao Tong University
Xidian University
TU: Tianjin University

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 February 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

Jilin Province Science and Technology Development Plan Projects

Conference

ICVIP 2019

ICVIP 2019: 2019 the 3rd International Conference on Video and Image Processing

December 20 - 23, 2019

Shanghai, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
217
Total Downloads

Downloads (Last 12 months)53
Downloads (Last 6 weeks)7

Reflects downloads up to 14 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Qiu LRahman ADolah MGe S(2024)The Research on the Application of Artificial Intelligence in Visual Art- based on Souvenir DesignWSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS10.37394/23209.2024.21.621(55-64)Online publication date: 14-Feb-2024
https://doi.org/10.37394/23209.2024.21.6
Guo KWu ZWang WRen SZhou XGadekallu TLuo ELiu C(2024)GRTR: Gradient Rebalanced Traffic Sign Recognition for Autonomous VehiclesIEEE Transactions on Automation Science and Engineering10.1109/TASE.2023.327020221:3(2349-2361)Online publication date: Jul-2024
https://doi.org/10.1109/TASE.2023.3270202
Zhou FZu HLi YSong YLiao JZheng C(2023)Traffic-Sign-Detection Algorithm Based on SK-EVC-YOLOMathematics10.3390/math1118387311:18(3873)Online publication date: 11-Sep-2023
https://doi.org/10.3390/math11183873
Alam MZhang SYakopcic CTaha T(2023)Memristor Based Online Learning Neuromorphic Processor for Adaptive Modulation Spectrum Sensing in Communication Jammed EnvironmentsNAECON 2023 - IEEE National Aerospace and Electronics Conference10.1109/NAECON58068.2023.10366022(73-79)Online publication date: 28-Aug-2023
https://doi.org/10.1109/NAECON58068.2023.10366022
Kheder MMohammed A(2023)Improved traffic sign recognition system (itsrs) for autonomous vehicle based on deep convolutional neural networkMultimedia Tools and Applications10.1007/s11042-023-15898-683:22(61821-61841)Online publication date: 27-May-2023
https://doi.org/10.1007/s11042-023-15898-6
Bouguezzi SBen Fredj HFaiedh HSouani C(2022)Improved architecture for traffic sign recognition using a self-regularized activation function: SigmaHThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-021-02211-538:11(3747-3764)Online publication date: 1-Nov-2022
https://dl.acm.org/doi/10.1007/s00371-021-02211-5
Zaibi ALadgham ASakly A(2021)A Lightweight Model for Traffic Sign Classification Based on Enhanced LeNet-5 NetworkJournal of Sensors10.1155/2021/88705292021(1-13)Online publication date: 29-Apr-2021
https://doi.org/10.1155/2021/8870529
Jena BNayak GSaxena S(2021)Convolutional neural network and its pretrained models for image classification and object detection: A surveyConcurrency and Computation: Practice and Experience10.1002/cpe.676734:6Online publication date: 13-Dec-2021
https://doi.org/10.1002/cpe.6767
Kheder MMohammed a(undefined)Improved Traffic Sign Recognition System (Itsrs) for Autonomous Vehicle Based on Deep Convolutional Neural NetworkSSRN Electronic Journal10.2139/ssrn.4135313
https://doi.org/10.2139/ssrn.4135313

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Two-Stage Traffic Sign Classification System

Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5

Digital Recognition Based on Improved LENET Convolution Neural Network