Abstract
Brazil is undergoing a gradual change in the format of its license plates from the old Brazilian model to the new Mercosur model. The proposed study addresses a fully automatic process, using the Detectron2 network for the classification of plate types, combined with the Haar Cascade method for detecting the region of interest and the perspective adjustment method for plate alignment using Tesseract-OCR for character recognition. The results show an accuracy of 95.48% for the classification of the plate type, obtaining satisfactory results with 98.00% of accuracy with the perspective adjustment method, against 93.00% without the adjustment, and 87.71% and 87.46% character recognition without and with perspective adjustment respectively. Thus, presenting great effectiveness compared to the work found in the literature.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Y. Y. Lee, Z. Abdul Halim, and M. N. Ab Wahab, “License plate detection using convolutional neural network-back to the basic with design of experiments,” IEEE Access, vol. 10, pp. 22 577–22 585, 2022
S. Ibadov, R. Ibadov, B. Kalmukov, and V. Krutov, “Algorithm for detecting violations of traffic rules based on computer vision approaches,” MATEC Web of Conferences, vol. 132, p. 05005, 01 2017
P. Mukhija and P. Dahiya, “Challenges in automatic license plate recognition system: An indian scenario,” 07 2021
D. R. L. V. E. R. Laroca, E. V. Cardoso and D. Menotti, “On the cross-dataset generalization in license plate recognition,” in VISAPP, 2022, pp. 166–178
L. Cuimei, Q. Zhiliang, J. Nan, and W. Jianhua, “Human face detection algorithm via haar cascade classifier combined with three additional classifiers,” in 2017 13th IEEE International Conference on Electronic Measurement & Instruments (ICEMI), 2017, pp. 483–487
Viola, P. and Jones, M., “Rapid object detection using a boosted cascade of simple features,” in Proceedings of the 2001 IEEE. CVPR 2001, vol. 1, Apr. 2001, pp. I–I
R. Raghavan, D. C. Verma, D. Pandey, R. Anand, B. K. Pandey, and H. Singh, “Optimized building extraction from high-resolution satellite imagery using deep learning,” Multimedia Tools and Applications, pp. 1–15, 2022
Sindhwani, N., Anand, R., Meivel, S., Shukla, R., Yadav, M.P., Yadav, V.: Performance analysis of deep neural networks using computer vision. EAI Endorsed Transactions on Industrial Networks and Intelligent Systems 8(29), e3–e3 (2021)
A. N. Yumang, M. Chloe M. Sta. Juana, and R. L. C. Diloy, “Detection and classification of defective fresh excelsa beans using mask r-cnn algorithm,” in 2022 14th International Conference on Computer and Automation Engineering (ICCAE), 2022, pp. 97–102
M. Valdeos, A. S. Vadillo Velazco, M. G. Pérez Paredes, and R. M. Arias Velásquez, “Methodology for an automatic license plate recognition system using convolutional neural networks for a peruvian case study,” IEEE Latin America Transactions, vol. 20, no. 6, p. 1032-1039, Mar. 2022
S.-H. Park, S.-B. Yu, J.-A. Kim, and H. Yoon, “An all-in-one vehicle type and license plate recognition system using yolov4,” Sensors, vol. 22, p. 921, 01 2022
Pham, V., Pham, C., Dang, T.: “Road damage detection and classification with detectron2 and faster r-cnn,” in. IEEE International Conference on Big Data (Big Data) 2020, 5592–5601 (2020)
C. M. G. Sabóia, A. G. Marques, L. F. de F. Souza, S. A. Peixoto, M. A. dos Santos, A. C. da Silva Barros, P. A. L. Rego, and P. P. R. Filho, “Fully automatic lpr method using haar cascade and perspective adjustment for real mercosur license plates,” Submitted for publication
C. M. G. Sabóia, Filho, and P. P. Rebouças, “Brazilian mercosur license plate detection and recognition using haar cascade and tesseract ocr on synthetic imagery.”
Dome, S., Sathe, A.P.: “Optical charater recognition using tesseract and classification,” in. International Conference on Emerging Smart Computing and Informatics (ESCI) 2021, 153–158 (2021)
M. Audichya and J. Saini, “A study to recognize printed gujarati characters using tesseract ocr,” Engineering, Technology and Applied Science Research, vol. 5, pp. 1505–1510, 09 2017
L. F. de F. Souza, C. M. G. Sabóia, A. G. Marques, J. da Costa Nascimento, A. C. d. S. B. Matheus A. dos Santos, P. A. L. Rego, and P. P. R. Filho, “New approach to the detection and recognition of brazilian mercosur plates using haar cascade and tesseract ocr in real images,” vol. 17, pp. 144–153, 2022
Acknowledgement
The authors would like to thank The Ceará State Foundation for the Support of Scientific and Technological Development (FUNCAP) for the financial support (grant #6945087/2019).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
de F. Souza, L.F. et al. (2023). New Approach in LPR Systems Using Deep Learning to Classify Mercosur License Plates with Perspective Adjustment. In: Abraham, A., Pllana, S., Casalino, G., Ma, K., Bajaj, A. (eds) Intelligent Systems Design and Applications. ISDA 2022. Lecture Notes in Networks and Systems, vol 715. Springer, Cham. https://doi.org/10.1007/978-3-031-35507-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-35507-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35506-6
Online ISBN: 978-3-031-35507-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)