Implementation and evaluation of an OCR system for vehicle license plate identification in a NAO humanoid robot

a proof of concept

Authors

DOI:

https://doi.org/10.47385/cadunifoa.v21.n56.6305

Keywords:

Vehicle License Plate Identification, Deep Learning, Computer Vision, NAO Robot, Humanoid Robotics, Optical Character Recognition

Abstract

This work describes the development and evaluation of an integrated optical character recognition (OCR) system for the NAO humanoid robot, focusing on the real-time identification of Brazilian vehicle license plates in a controlled environment. The system uses the EasyOCR library based on deep learning, integrated into the NAO's qi framework through an off-board architecture for remote processing via WiFi, with image capture by the front camera at VGA resolution at 15 FPS. Five experimental cases were conducted in a controlled environment, with processing times ranging from 0.070 s to 0.345 s. The results indicate that the text region detection module operates with greater robustness than the character classification module, with the accuracy of the latter being strongly influenced by the visual quality of the image, contrast, and compositional complexity of the license plate. The average confidence of the detections was 0.75 (standard deviation of 0.25), with variations between simple and complex cases. The results establish a baseline for the development of OCR systems on humanoid robotic platforms and point to image preprocessing as the main area for improvement in future work.

Downloads

Download data is not yet available.

Author Biography

Vitor Amadeu Souza, UniFOA, Centro Universitário de Volta Redonda, Volta Redonda, RJ, Brazil

Doutorando em Engenharia de Defesa pelo IME e mestre em Física pelo CBPF, possui formação multidisciplinar em engenharias, computação, elétrica, eletrônica, ciência de dados, inteligência artificial, automação e gestão de projetos. Atua há vários anos no desenvolvimento de projetos de hardware e software para os setores industrial, automotivo, médico, científico, comercial e de automação. É professor universitário e administrador da Cerne Tecnologia, empresa voltada ao desenvolvimento de sistemas embarcados, kits didáticos e educação tecnológica. Também é associado à SBC, SBIA e SBR, além de autor de vasta produção técnica e científica nas áreas de eletrônica, computação, automação e tecnologias digitais.

References

ALDEBARAN ROBOTICS. NAO Technical Documentation. Softbank Robotics, 2021. Disponível em: http://doc.aldebaran.com/2-8/home_nao.html. Acesso em: 2 set. 2025.

ANAGNOSTOPOULOS, Christos-Nikolaos E. et al. License plate recognition from still images and video sequences: A survey. IEEE Transactions on Intelligent Transportation Systems, v. 9, n. 3, p. 377-391, 2008. DOI: https://doi.org/10.1109/TITS.2008.922938

BAEK, Y.; LEE, B.; HAN, D.; YOON, S.; LEE, H. Character region awareness for text detection. In: PROCEEDINGS OF THE IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, 2019, Long Beach. Anais... Long Beach: IEEE, 2019. p. 9365-9374. DOI: 10.1109/CVPR.2019.00959. DOI: https://doi.org/10.1109/CVPR.2019.00959

BLANSON HENKEMANS, O. NAO robot by Aldebaran Robotics. 2025. Disponível em: [https://www.aldebaran.com/en/nao](https://www.aldebaran.com/en/nao). Acesso em: 21 maio 2026.

CHEN, Li et al. Beyond human recognition: A CNN-based framework for handwritten character recognition. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR). IEEE, 2015. p. 695-699. DOI: https://doi.org/10.1109/ACPR.2015.7486592

CHEN, Song et al. A real-time face detection and recognition system for a mobile robot in a complex background. Artificial Life and Robotics, v. 15, n. 4, p. 439-443, 2010. DOI: https://doi.org/10.1007/s10015-010-0838-z

FICHT, Grzegorz et al. NimbRo-OP2X: Adult-sized open-source 3D printed humanoid robot. In: 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids). IEEE, 2018. p. 1-9. DOI: https://doi.org/10.1109/HUMANOIDS.2018.8625038

GOUAILLIER, D.; HUGEL, V.; BLAZEVIC, P.; KILNER, C.; MONCEAUX, J.; LAFOURCADE, P.; MARNIER, B.; SERRE, J.; MAISONNIER, B. Mechatronic design of NAO humanoid. In: IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, 2009, Kobe. Proceedings... Kobe: IEEE, 2009. p. 769-774. DOI: 10.1109/ROBOT.2009.5152516. Disponível em: https://ieeexplore.ieee.org/document/5152516. Acesso em: 10 set. 2024. DOI: https://doi.org/10.1109/ROBOT.2009.5152516

GOUAILLIER, David et al. The nao humanoid: a combination of performance and affordability. arXiv preprint arXiv:0807.3223, 2008.

HEREMANS, François et al. Bio-inspired balance controller for a humanoid robot. In: IEEE INTERNATIONAL CONFERENCE ON BIOMEDICAL ROBOTICS AND BIOMECHATRONICS, 6., 2016. Anais... IEEE, 2016. p. 441-448. DOI: https://doi.org/10.1109/BIOROB.2016.7523667

GURUPRASAD, Arvind; PAUL RAJ, Kevin; NAGARATHNA, N. Automatic License Plate Recognition Under Harsh Conditions. In: Soft Computing and Signal Processing: Proceedings of 3rd ICSCSP 2020, Volume 1. Singapore: Springer Singapore, 2021. p. 705-716.

LG ELECTRONICS. Monitor TV LED LCD 21.5'' M2280A. 2025. Disponível em: https://www.lg.com. Acesso em: 21 maio 2026.

LI, Hui et al. Show, attend and read: A simple and strong baseline for irregular text recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2019. p. 8610-8617. DOI: https://doi.org/10.1609/aaai.v33i01.33018610

LONG, S.; HE, X.; YAO, C. Scene text detection and recognition: The deep learning era. International Journal of Computer Vision, New York, v. 129, n. 1, p. 161-184, 2020. DOI: 10.1007/s11263-020-01369-0. Disponível em: https://link.springer.com/article/10.1007/s11263-020-01369-0. Acesso em: 11 set. 2024. DOI: https://doi.org/10.1007/s11263-020-01369-0

LUO, Jing et al. Robotics perception and control: Key technologies and applications. Micromachines, v. 15, n. 4, p. 531, 2024. DOI: https://doi.org/10.3390/mi15040531

MAGALLÁN-RAMÍREZ, D. et al. Implementation of NAO Robot Maze Navigation Based on Computer Vision and Collaborative Learning. Frontiers in Robotics and AI, v. 9, p. 834021, 2022. DOI: 10.3389/frobt.2022.834021. DOI: https://doi.org/10.3389/frobt.2022.834021

MANAKITSA, Nikoleta et al. A review of machine learning and deep learning for object detection, semantic segmentation, and human action recognition in machine and robotic vision. Technologies, v. 12, n. 2, p. 15, 2024. DOI: https://doi.org/10.3390/technologies12020015

MEMON, Jamshed et al. Handwritten optical character recognition (OCR): A comprehensive systematic literature review (SLR). IEEE Access, v. 8, p. 142642-142668, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.3012542

MONTAZZOLLI, Sérgio; JUNG, Claudio. Real-time brazilian license plate detection and recognition using deep convolutional neural networks. In: 2017 30th SIBGRAPI Conference on Graphics, patterns and Images (SIBGRAPI). IEEE, 2017. p. 55-62. DOI: https://doi.org/10.1109/SIBGRAPI.2017.14

WANG, Tianwei et al. Decoupled attention network for text recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2020. p. 12216-12224. DOI: https://doi.org/10.1609/aaai.v34i07.6903

WIKIPEDIA. Placas de identificação de veículos no Brasil. 2025. Disponível em: https://pt.wikipedia.org/wiki/Placas_de_identifica%C3%A7%C3%A3o_de_ve%C3%ADculos_no_Brasil. Acesso em: 21 maio 2026.

Published

2026-10-13

How to Cite

SOUZA, Vitor Amadeu. Implementation and evaluation of an OCR system for vehicle license plate identification in a NAO humanoid robot: a proof of concept. Cadernos UniFOA, Volta Redonda, RJ, v. 21, n. 56, p. 18, 2026. DOI: 10.47385/cadunifoa.v21.n56.6305. Disponível em: https://revistas.unifoa.edu.br/cadernos/article/view/6305. Acesso em: 19 oct. 2026.

Issue

Section

Tecnologia e Engenharias