Sistema de monitoreo vehicular para automóviles mediante reconocimiento de caracteres en placas y evaluación de sanciones con lógica difusa Mamdani
DOI:
https://doi.org/10.63957/arksis.v1i2.0011Palabras clave:
Visión computacional, reconocimiento de placas, lógica difusa Mamdani, aprendizaje profundo, apoyo a la decisiónResumen
En recintos institucionales, identificar los vehículos y revisar su velocidad suele realizarse de forma manual, lo cual es lento y propenso a errores. Se desarrolló un sistema de visión computacional que integra el proceso en un solo flujo: la placa se detecta con YOLOv11n, los caracteres se segmentan con una U-Net y se clasifican con una CNN, se comprueba el formato de placa ecuatoriana, se estima la velocidad con dos líneas virtuales y un sistema difuso Mamdani pondera el exceso de velocidad y la reincidencia para sugerir una sanción gradual e interpretable. El clasificador alcanzó 91.42% de exactitud sobre un conjunto de prueba de 5877 recortes y, en 74 vehículos reales, la placa completa se leyó correctamente con 94.59% de exactitud. La integración de estas etapas es viable y apoya al operador sin reemplazar su criterio.
Referencias
[1] E. Dilek and M. Dener, "Computer vision applications in intelligent transportation systems: A survey," Sensors, vol. 23, no. 6, p. 2938, 2023, doi: 10.3390/s23062938.
[2] A. Ammar, A. Koubaa, W. Boulila, B. Benjdira and Y. Alhabashi, "A multi-stage deep-learning-based vehicle and license plate recognition system with real-time edge inference," Sensors, vol. 23, no. 4, p. 2120, 2023, doi: 10.3390/s23042120.
[3] M. Safran, A. Alajmi and S. Alfarhood, "Efficient multistage license plate detection and recognition using YOLOv8 and CNN for smart parking systems," Journal of Sensors, vol. 2024, p. 4917097, 2024, doi: 10.1155/2024/4917097.
[4] Sutikno, A. Sugiharto and R. Kusumaningrum, "Enhanced automatic license plate detection and recognition using CLAHE and YOLOv11 for seat belt compliance detection," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 20271-20278, 2025, doi: 10.48084/etasr.9629.
[5] R. J. Tom, A. Kumar, S. Shaik, L. D. Isaac, V. Tripathi and P. Pareek, "Car license plate detection and recognition using modified U-Net deep learning model," in 8th International Conference on Smart Structures and Systems (ICSSS), 2022, doi: 10.1109/ICSSS54381.2022.9782176.
[6] M. Salemdeeb and S. Ertürk, "Full depth CNN classifier for handwritten and license plate characters recognition," PeerJ Computer Science, vol. 7, p. e576, doi: 10.7717/peerj-cs.576.
[7] H. Moussaoui, N. El Akkad, M. Benslimane, W. El-Shafai, A. Baihan , C. Hewage and R. S. Rathore , "Enhancing automated vehicle identification by integrating YOLO v8 and OCR techniques for high-precision license plate detection and recognition," Scientific Reports, vol. 14, p. 14389, 2024, doi: 10.1038/s41598-024-65272-1.
[8] R. Li, "A multi-stage deep learning approach for real-time vehicle detection, tracking, and speed measurement in intelligent transportation systems," Scientific Reports, vol. 15, p. 22531, 2025, doi: 10.1038/s41598-025-07343-5.
[9] M.-D. Pop , D. Pescaru and M. V. Micea , "Mamdani vs. Takagi-Sugeno fuzzy inference systems in the calibration of continuous-time car-following models," Sensors, vol. 23, no. 21, p. 8791, 2023, doi: 10.3390/s23218791.
[10] A. Kaur , J. Williams , R. Recker , D. Rose , M. Zhu and J. Yang , "Subsequent risky driving behaviors, recidivism and crashes among drivers with a traffic violation: A scoping review," Accident Analysis & Prevention, vol. 192, p. 107234, 2023, doi: 10.1016/j.aap.2023.107234.
[11] B. Satya , D. Manongga , Hendry and A. Aminuddin , "Optimized YOLOv8 for automatic license plate recognition on resource constrained devices," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 21976-21981, 2025, doi: 10.48084/etasr.9983.
[12] Roboflow Universe Projects, "License Plate Recognition Dataset (v13)," January 2026. [Online]. Available: https://universe.roboflow.com/roboflow-universe-projects/license-plate-recognition-rxg4e.
[13] student-tfefc, "LPR Character Segmentation Dataset (v3)," May 2025. [Online]. Available: https://universe.roboflow.com/student-tfefc/lpr-character-segmentation.
[14] guilhermecoleta, "Plate-OCR Dataset (v4)," July 2025. [Online]. Available: https://universe.roboflow.com/guilhermecoleta/plate-ocr-wb6jn.
[15] university-uk, "EN - License Plate Characters Dataset (v4)," September 2023. [Online]. Available: https://universe.roboflow.com/university-uk/en-t0yqi.
[16] wilsons-workspace-andqz, "Modelo_DeteccionPlacasEc Dataset (v3)," April 2026. [Online]. Available: https://universe.roboflow.com/wilsons-workspace-andqz/modelo_deteccionplacasec.
[17] Axis Communications, "License plate capture: Key factors for successful license plate recognition," Axis Communications, 2019.
[18] International Electrotechnical Commission (IEC), "IEC 62676-4: Video surveillance systems for use in security applications — Part 4: Application guidelines," IEC, 2014.
[19] "Communication in the presence of noise," Proceedings of the IRE, vol. 37, no. 1, pp. 10-21, 1949, doi: 10.1109/JRPROC.1949.232969.
[20] O. Ronneberger , P. Fischer and T. Brox , "U-Net: Convolutional networks for biomedical image segmentation," in Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), Lecture Notes in Computer Science, vol. 9351, 2015, doi: 10.1007/978-3-319-24574-4_28.
[21] K. Simonyan and A. Zisserman , "Very deep convolutional networks for large-scale image recognition," in International Conference on Learning Representations (ICLR), 2015, doi: 10.48550/arXiv.1409.1556.
[22] N. Srivastava , G. Hinton , A. Krizhevsky , I. Sutskever and R. Salakhutdinov , "Dropout: A simple way to prevent neural networks from overfitting," Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
[23] Consultas Ecuador, "Placas de Autos en Ecuador," 2023. [Online]. Available: https://consultasecuador.com/blog/ver/placas-de-autos-en-ecuador.
[24] L. A. Zadeh, "Fuzzy sets," Information and Control, vol. 8, no. 3, pp. 338-353, 1965, doi: 10.1016/S0019-9958(65)90241-X.
[25] V. Kreinovich , O. Kosheleva and S. N. Shahbazova , "Why triangular and trapezoid membership functions: A simple explanation," in Recent Developments in Fuzzy Logic and Fuzzy Sets (Studies in Fuzziness and Soft Computing, vol. 391), Springer, 2020, pp. 25-31, doi: 10.1007/978-3-030-38893-5_2.
[26] S. Assilian and E. H. Mamdani, "An experiment in linguistic synthesis with a fuzzy logic controller," International Journal of Man-Machine Studies, vol. 7, no. 1, pp. 1-13, 1975, doi: 10.1016/S0020-7373(75)80002-2.
[27] O. Rainio , J. Teuho and R. Klén , "Evaluation metrics and statistical tests for machine learning," Scientific Reports, vol. 14, p. 6086, 2024, doi: 10.1038/s41598-024-56706-x.
[28] W. G. Cochran, Sampling Techniques, New York: John Wiley & Sons, 1977.
[29] T.-Y. Lin, P. Goyal , R. Girshick , K. He and P. Dollár , "Focal loss for dense object detection," in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, doi: 10.1109/ICCV.2017.324.
Publicado
Número
Sección
Categorías
Licencia
Derechos de autor 2026 Revista de Ingeniería, Industria y Construcción
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Revista Multidisciplinaria de Ingeniería e Industria © 2025 by PUCE sede Ambato está licenciada bajo CC BY 4.0
Los artículos publicados en ARKSIS se distribuyen bajo los términos de la Licencia Creative Commons Atribución 4.0 Internacional (CC BY 4.0), en específico los términos de la licencia oficial otorga permisos para:
A. Libertades que Usted Recibe (Derechos del Licenciatario):
- Compartir: Copiar, redistribuir el material en cualquier medio o formato.
- Adaptar: Remezclar, transformar y crear a partir del material para cualquier propósito, incluido el comercial.
B. Condición Única y Obligatoria:
- Atribución (BY): Debe dar el crédito al autor de la manera especificada por el licenciante (la revista).
Así, en específico esta licencia permite crear obras derivadas (traducciones, resúmenes ampliados, nuevos análisis basados en los datos), para lo que es importante destacar:
- Integridad Académica: Cualquier modificación debe ser claramente identificada como tal.
- Atribución de la Fuente Original: La obra derivada debe citar el trabajo original de la forma especifica.
- No Endoso Implícito: El hecho de permitir adaptaciones no significa que los autores o la revista avalen la obra derivada o su uso.
