CFP last date
22 June 2026
Call for Paper
July Edition
IJCA solicits high quality original research papers for the upcoming July edition of the journal. The last date of research paper submission is 22 June 2026

Submit your paper
Know more
The week's pick
Responsive image
Multi-Band RLS Estimation with Rank Two Updates: Application to Short-Term Temperature Forecast

Alexander Stotsky
Random Articles
Reseach Article

Variance-based License Plate Detection with Modified LeNet-5 Architecture for Real-Time Automatic Number Plate Recognition

by Mayank, Kamlesh Dutta
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 187 - Number 103
Year of Publication: 2026
Authors: Mayank, Kamlesh Dutta
10.5120/ijca00c485e54bd6

Mayank, Kamlesh Dutta . Variance-based License Plate Detection with Modified LeNet-5 Architecture for Real-Time Automatic Number Plate Recognition. International Journal of Computer Applications. 187, 103 ( May 2026), 48-53. DOI=10.5120/ijca00c485e54bd6

@article{ 10.5120/ijca00c485e54bd6,
author = { Mayank, Kamlesh Dutta },
title = { Variance-based License Plate Detection with Modified LeNet-5 Architecture for Real-Time Automatic Number Plate Recognition },
journal = { International Journal of Computer Applications },
issue_date = { May 2026 },
volume = { 187 },
number = { 103 },
month = { May },
year = { 2026 },
issn = { 0975-8887 },
pages = { 48-53 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume187/number103/variance-based-license-plate-detection-with-modified-lenet-5-architecture-for-real-time-automatic-number-plate-recognition/ },
doi = { 10.5120/ijca00c485e54bd6 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2026-05-17T02:29:11.160533+05:30
%A Mayank
%A Kamlesh Dutta
%T Variance-based License Plate Detection with Modified LeNet-5 Architecture for Real-Time Automatic Number Plate Recognition
%J International Journal of Computer Applications
%@ 0975-8887
%V 187
%N 103
%P 48-53
%D 2026
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Automatic Number Plate Recognition (ANPR) is a fundamental technology in modern intelligent transportation systems, enabling automated vehicle identification for traffic management, toll collection, law enforcement, and security applications. The challenge is particularly pronounced in developing countries such as India, where license plate standards are inconsistently enforced, resulting in substantial variation in plate size, color, font, and physical condition. This paper presents a fully automated real-time ANPR system comprising four modules: (a) vehicle detection using background subtraction, (b) license plate localization using a novel variance-based technique, (c) character segmentation using horizontal and vertical projection, and (d) character recognition using a modified LeNet-5 convolutional neural network (CNN) architecture. The proposed variance-based localization algorithm divides the input grayscale image into fixed-size 5×5 blocks and identifies the license plate region by comparing each block’s pixel intensity variance against an adaptive threshold, exploiting the high-contrast alphanumeric content unique to license plate regions. A modified LeNet-5 architecture is also introduced that reduces the number of convolutional feature maps, significantly decreasing processing time while preserving accuracy. The system was evaluated on the Media Lab Dataset comprising 571 vehicle images across eight categories of varying illumination conditions. Results demonstrate a license plate detection accuracy of 98.04% and a character recognition accuracy of 93.21% at 0.55ms processing time, confirming suitability for real-time deployment.

References
  1. Mandellos, N. A., Keramitsoglou, I., and Kiranoudis, C. T. 2010. A background subtraction algorithm for detecting and tracking vehicles. Expert Systems with Applications. 38(3), 1619–1631. DOI: 10.1016/j.eswa.2010.07.083.
  2. Hu W, Tan T, Wang L, Maybank S. A survey on visual surveillance of object motion and behaviors. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews). 2004 Aug;34(3):334-352. doi:10.1109/TSMCC.2004.829274.
  3. Kim K, Kim K, Kim J, Kim H. Learning-based approach for license plate recognition. In: Proceedings of the IEEE Neural Networks for Signal Processing Conference. 2000;2:614-623. doi:10.1109/NNSP.2000.890140.
  4. Ammar A, Koubaa A, Boulila W, Benjdira B, Alhabashi Y. A multi-stage deep-learning-based vehicle and license plate recognition system with real-time edge inference. Sensors. 2023;23(4):2120. doi:10.3390/s23042120.
  5. Shashirangana J, Padmasiri H, Meedeniya D, Perera C. Automated license plate recognition: A survey on methods and techniques. IEEE Access. 2020;9:11203-11225. doi:10.1109/ACCESS.2020.3047929.
  6. Anagnostopoulos C, Anagnostopoulos I, Loumos V, Kayafas E. A license plate-recognition algorithm for intelligent transportation system applications. IEEE Transactions on Intelligent Transportation Systems. 2006 Sep;7(3):377-392. doi:10.1109/TITS.2006.880641.
  7. Fernández Sánchez, L. 2018. Automatic number plate recognition (ANPR) system using machine learning techniques. Master's Thesis, University of the Basque Country (UPV/EHU), Spain.
  8. Zheng D, Zhao Y, Wang J. An efficient method of license plate location. Pattern Recognition Letters. 2005;26(15):2431-2438.
  9. Rasheed S, Naeem A, Ishaq O. Automated number plate recognition using hough lines and template matching. In: Proceedings of the World Congress on Engineering and Computer Science. 2012;1:24-26.
  10. Kim SK, Kim DW, Kim HJ. A recognition of vehicle license plate using a genetic algorithm5 based segmentation. In: Proceedings of the IEEE International Conference on Image Processing. IEEE; 1996. p. 661-664. doi:10.1109/ICIP.1996.560964.
  11. Jia W, Zhang H, He X. Region-based license plate detection. Journal of Network and Computer Applications.2007;30(4):1324-1333.
  12. Porikli F, Kocak T. Robust license plate detection using covariance descriptor in a neural network framework. In: Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance. IEEE; 2006. p. 107. doi:10.1109/AVSS.2006.100.
  13. Nakano T, Fukumi M, Khalid M. Vehicle license plate character recognition by neural networks. In: Proceedings of the IEEE International Symposium on Intelligent Signal Processing and Communication Systems. IEEE; 2004. p. 771-775. doi:10.1109/ISPACS.2004.1439164.
  14. LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE. 1998 Nov;86(11):2278-2324.
  15. Radzi, S. A. and Khalil-Hani, M. 2011. Character recognition of license plate number using convolutional neural network. In Proc. Int. Vis. Informatics Conf., 45–55.
  16. Burkpalli AV, Joshi A, Warad AB, Patil A. Automatic number plate recognition using TensorFlow and EasyOCR. International Research Journal of Modernization in Engineering, Technology and Science. 2022;4(9):493-501.
  17. Yepez J, Ko S. Improved license plate localisation algorithm based on morphological operations. IET Intelligent Transport Systems. 2018;12(6):542-549. doi:10.1049/iet-its.2017.0224.
  18. Zhai X, Bensaali F, Ramalingam S. Improved number plate localisation algorithm and its efficient field programmable gate arrays implementation. IET Circuits, Devices & Systems. 2013;7(2):93-103. doi:10.1049/iet-cds.2012.0064.
  19. Tao, L., Hong, S., Lin, Y., Chen, Y., He, P., and Tie, Z. 2024. A real-time license plate detection and recognition model in unconstrained scenarios. Sensors. 24(9), 2791. DOI: 10.3390/s24092791.
  20. Meesad, P., and Thumthong, W. 2025. Advanced deep learning techniques for automated license plate recognition. Scientific Reports. 15(1), 41194. DOI: 10.1038/s41598-025-24967-9.
  21. Sonnara, F., Chihaoui, H., and Filali, F. 2025. Efficient real-time license plate recognition using deep learning on edge devices. Journal of Real-Time Image Processing. 22(4). DOI: 10.1007/s11554-025-01738-3.
Index Terms

Computer Science
Information Sciences

Keywords

Automatic Number Plate Recognition; ANPR; License Plate Detection; Convolutional Neural Network; LeNet-5; Variance Based Detection; Character Segmentation; Real-Time Processing

Powered by PhDFocusTM