INTRODUCTION
Nowadays,
computer vision has a wide range of applications in object recognition, one of
these is vehicle license plate recognition systems (LPR), which seek to
recognize license plates in a non-intrusive way; that is, they use devices
external to the car to monitor and locate the car (Weihong el al., 2020). The
device par excellence for these systems is the camera, which can acquire static
or dynamic images; cameras are sometimes enhanced with infrared technology to
reduce factors that affect detection, for example environmental conditions or
the time of day. Ideally, an LPR system should be optimized with recognition
algorithms that allow it to work in real time and under real conditions in the
field where it is applied, thus achieving an assertive and instantaneous
response to the analysis carried out in a traffic context (Valencia et al.,
2020).
Moreover, we
have new models for Artificial Intelligence (AI) that can be perceived in
different applications, such as voice recognition in vehicles (Prongnuch &
Sitjongsataporn, 2020), recognition of traffic signs (Rodríguez et al., 2020;
Calero et al., 2021), among others (Virgilio et al., 2020). As a plus,
technological advances in hardware, in conjunction with these new AI models,
have resulted in the development of new and hybrid algorithms, which seek the
solution of different problems such as lighting (Mattoo et al., 2021), angles
(Wijaya et al., 2020), real time (Benitez-Garcia et al., 2021), tracking
(López-Monroy et al., 2021), among many others (Janai et al., 2020).
In recent years,
the need to improve security in different contexts of society has led to the
development of new computer systems and equipment (Karande & Joshi, 2020).
Security through AI is an area of interest, which provides us with a completely
new dimension to the intelligent tracking and navigation industry, to include
route optimization (Díaz-Parra et al., 2020), vehicle function control
(Receveur et al., 2020) and theft reduction (Prasad et al., 2020), among others
(Martínez-Cruz et al., 2021).
In Vijayalakshmi
et al. (2021) propose a model for vehicle identification and tracking, based on
the global positioning system (GPS). For this case, the GPS support device
moves continuously with the vehicle and will calculate the coordinates of each
position.
In the same way,
Dang et al. (2021) proposes security systems against possible theft. In fact,
vehicle manufacturing companies are incorporating different methods to provide
better security mechanisms. In particular, vehicle safety can be carried out by
implementing GPS and GSM (Global System for Mobile Communication) technologies.
Additionally, automatic features have been incorporated to slow down vehicles
in school or hospital zones (Sathiskumar et al., 2020; Zade et al., 2018).
License plate
recognition is the system where computer vision technology identifies the
license plate number from an image without human intervention (Xiao et al.,
2020). Design for this type of system is not an easy task, due to the different
styles and characteristics of license plates. Some of the most important
characteristics to consider in the recognition and detection of the numbers and
letters on license plates include: lighting, quality, angle and the style of
the typeface font and numbers on the license plate (Asif et al., 2017).
Automatic
vehicle identification has become increasingly important for many applications;
for example, parking fees (Farag et al., 2019), payment of tolls (Ahmed et al.,
2019), traffic surveillance (Gupta et al., 2020), ticketing (Blythe, 2004),
access control (Wijnhoven et al., 2011) , among others. A license plate is a
unique feature by which to identify each individual vehicle. Automatic vehicle
license plate recognition, as a research area has already been extensively
studied, over several decades (Shashirangana et al., 2020).
Although
significant progress has been made in license plate recognition techniques
during the last decade, it is still a challenging task to recognize license
plates from complex images, as a profficient system should function effectively
under a variety of conditions, such as on a sunny day or at night, or with
different colors and complex backgrounds. Selmi, et al. (2020) indicated that
Automatic License Plate Detection and Recognition (ALPR) is employed to make
detection and recognition processes more robust and efficient in very
challenging environments, necessitating further investigation due to some
limitations such as: integrity of numbering systems in countries, where colors,
languages, sizes and fonts vary.
METHODOLOGY
The process for
the automatic recognition of license plates begins with the acquisition of the
image from a scene in three dimensions; this image is then processed to improve
its quality and eliminate any possible imperfections; the next step is to
separate the object of interest from the background, followed by the extraction
of the characteristics that describe the object (color, texture and geometry).
In this
investigation, we undertake a comparison of intelligent algorithms for license
plate recognition. The aim is to determine which of these algorithms represents
the best alternative for achieving optimal identification of Mexico City number
plates.
Our solution
using a ten-phase model is shown in Figure 1:
CONCLUSIONS
The analysis of large
quantities of data based on pattern recognition and learning algorithms have
helped enormously and opened the door to new possibilities. However, this is
just the tip of the iceberg; the tendency is moving towards artificial and
autonomous intelligent systems that are continually learning from the data, in
order to make optimal analytical decisions.
Despite the fact that the
KNN algorithm is very tolerant to noise, SVM has the highest success rate in
terms of detecting Mexico City license plates, with 84% effectiveness; the
margin of error for one hundred and fifty-three cases, apparently indicated only
one letter incorrectly, meaning five characters were correctly identified and
that the letter which was most often confused with the classifier was the
letter "T" with number "1". Thus future work will involve
evaluating different computer vision techniques, together with a variety of
neural networks that employ more complex images.
REFERENCIAS BIBLIOGRÁFICAS
[1]
Ahmed, S., Tan, T. M., Mondol, A. M., Alam, Z.,
Nawal, N., & Uddin, J. (2019). Automated toll collection system based on
rfid sensor. In 2019 International Carnahan Conference on Security Technology
(ICCST) (pp. 1-3). IEEE.
[2]
Asif, M. R., Chun, Q., Hussain, S., Fareed, M.
S., & Khan, S. (2017). Multinational vehicle license plate detection in
complex backgrounds. Journal of Visual Communication and Image Representation,
46, 176-186.
[3]
Benitez-Garcia, G., Prudente-Tixteco, L., Castro-Madrid, L. C.,
Toscano-Medina, R., Olivares-Mercado, J., Sanchez-Perez, G., & Villalba, L.
J. G. (2021). Improving real-time hand gesture recognition
with semantic segmentation. Sensors, 21(2), 356.
[4] Blythe, P. T. (2004). Improving public transport ticketing through
smart cards. In Proceedings of the Institution of Civil Engineers-Municipal
Engineer (Vol. 157, No. 1, pp. 47-54). Thomas Telford Ltd.
[5] Calero,
M. J. F., Sanchez, M. A., Vargas, J., & Ayala, M. J. (2021). Ecuadorian regulatory traffic sign detection by using HOG features
and ELM classifier. IEEE Latin America Transactions, 19(4), 634-642.
[6] Dang, T., Gupta, V., Wadia, D. S., Kohli, P., & Chahal, R. K.
(2021, March). FaceIgnition: An automatic anti-theft and keyless solution for
vehicles. In 2021 International Conference on Computational Intelligence and
Knowledge Economy (ICCIKE) (pp. 248-253). IEEE.
[7] Darapaneni,
N., Mogeraya, K., Mandal, S., Narayanan, A., Siva, P., Paduri, A. R., &
Agadi, P. M. (2020). Computer vision based license plate
detection for automated vehicle parking management system. In 2020 11th IEEE
Annual Ubiquitous Computing, Electronics & Mobile Communication Conference
(UEMCON) (pp. 0800-0805). IEEE.
[8] Díaz-Parra,
O., Ruiz-Vanoye, J. A., Fuentes-Penna, A., Zezzatti, A. O., Cruz-Hernández, E.,
Estrada-García, S., & Alvarado-Pérez, A. (2020). Editorial
for Volume 11 Number 2: Electric School Bus Routing Problem for Smart Cities. International
Journal of Combinatorial Optimization Problems and Informatics, 11(2), 1.
[9] Diaz-Ramirez,
V. H., & Juarez-Salazar, R. (2021, August). Multiple
object tracking in color scenes using composite-matched filtering with complex
constrains. In Optics and Photonics for Information Processing XV (Vol. 11841,
p. 118410J). International Society for Optics and Photonics
[10] Farag, M. S., El Din, M. M.,
& El Shenbary, H. A. (2019). Parking entrance control
using license plate detection and recognition. Indonesian Journal of
Electrical Engineering and Computer Science, 15(1), 476-483.
[11] Gupta,
A., Gandhi, C., Katara, V., & Brar, S. (2020). Real-time
video monitoring of vehicular traffic and adaptive signal change using
Raspberry Pi. In 2020 IEEE Students Conference on Engineering & Systems
(SCES) (pp. 1-5). IEEE.
[12] Janai, J.,
Güney, F., Behl, A., & Geiger, A. (2020). Computer vision for autonomous
vehicles: Problems, datasets and state of the art. Foundations and
Trends in Computer Graphics and Vision, 12(1–3), 1-308.
[13] Karande,
J., & Joshi, S. (2020, July). Real-Time Detection of Cyber Attacks on the
IoT Devices. In 2020 11th International Conference on Computing, Communication
and Networking Technologies (ICCCNT) (pp. 1-6). IEEE.
[14] Le, H., Liu, F., Zhang, S., & Agarwala, A. (2020). Deep
homography estimation for dynamic scenes. In Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition (pp. 7652-7661).
[15] Liu, W.,
Wei, J., & Meng, Q. (2020). Comparisions on KNN, SVM, BP and the CNN for
Handwritten Digit Recognition. In 2020 IEEE International Conference on
Advances in Electrical Engineering and Computer Applications (AEECA) (pp.
587-590). IEEE.
[16] López-Monroy, A. P.,
Elias-Miranda, A. A., Vallejo-Aldana, D., García-Carmona, J. M., &
Pérez-Espinosa, H. (2021). Deep Learning for Language and
Vision Tasks in Surveillance Applications. Computación y Sistemas,
25(2), 317-328.
[17] Makkar, T.,
Kumar, Y., Dubey, A. K., Rocha, Á., & Goyal, A. (2017). Analogizing time
complexity of KNN and CNN in recognizing handwritten digits. In 2017 Fourth
International Conference on Image Information Processing (ICIIP) (pp. 1-6). IEEE.
[18] Martínez-Cruz, A.,
Ramírez-Gutiérrez, K. A., Feregrino-Uribe, C., & Morales-Reyes, A. (2021). Security on in-vehicle communication protocols: Issues, challenges,
and future research directions. Computer Communications.
[19] Mattoo, A.,
Saxena, K., Kumar, S., & Bagwari, N. (2021). Design of IoT-Based Smart
Illumination System in Smart Cities. In Proceedings of 3rd International
Conference on Computing Informatics and Networks (pp. 517-528). Springer,
Singapore.
[20] Mirmozaffari,
M. (2020). Filtering in image processing. ENG transactions, vol 1. Mo, S., Gan,
H., Zhang, R., Yan, Y., & Liu, X. (2020, June). Edge Detection Method Based
on Hysteresis Connection and Prediction. In 2020 IEEE 4th Information
Technology, Networking, Electronic and Automation Control Conference (ITNEC)
(Vol. 1, pp. 1794-1798). IEEE.
[21] Prasad, S. K., Rachna, J.,
Khalaf, O. I., & Le, D. N. (2020). Map matching algorithm:
Real time location tracking for smart security application. Telecommunications
and Radio Engineering, 79(13).
[22] Prongnuch,
S., & Sitjongsataporn, S. (2020). Thai voice-controlled analysis for car
parking assistance in system-on-chip architecture. Advances in
Technology Innovation, 5(4), 203.
[23] Receveur,
J. B., Victor, S., & Melchior, P. (2020). Autonomous car decision making
and trajectory tracking based on genetic algorithms and fractional potential
fields. Intelligent Service Robotics, 13(2), 315-330.
[24] Rodríguez, R. C., Carlos, C.
M., Vergara-Villegas, O. O., & Sánchez, V. G. C. (2020). Detección y
clasificación de señales de tráfico mexicanas mediante aprendizaje profundo.
Res. Comput. Sci., 149(8), 435-449.
[25] San Hlaing, N. N., Naing, M., & San Naing, S. (2019). GPS and
GSM based vehicle tracking system. International Journal of Trend in Scientific
Research and Development (IJTSRD).
[26] Sathiskumar, S., Navean, G. V., Hari Prakash, R., & Vishnu
Praveen, S. (2020). Automatic Vehicle Speed Control System In A Restricted
Zone. International Journal Of Scientific & Technology Research, 9(02).
[27] Selmi, Z., Halima, M. B.,
Pal, U., & Alimi, M. A. (2020). DELP-DAR system for
license plate detection and recognition. Pattern Recognition Letters,
129, 213-223.
[28] Shashirangana, J.,
Padmasiri, H., Meedeniya, D., & Perera, C. (2020). Automated
license plate recognition: a survey on methods and techniques. IEEE
Access, 9, 11203-11225.
[29] Shukla, A.,
& Jain, A. (2018). GPS-Based Tracking System for Vehicles Using Google
Maps. IUP Journal of Electrical and Electronics Engineering, 11(4),
57-64.
[30] Valencia, J.,
Ramirez-Guerrero, T., Castañeda, L., & Toro, M. (2020). Detección de
infracciones y matrículas en motocicletas, mediante visión artificial, aplicado
a Sistemas Inteligentes de Transporte. Revista Ibérica de Sistemas e
Tecnologias de Informação, (37), 1-15.
[31] Vazquez-Nicolas, J. M.,
Zamora, E., González-Hernández, I., Lozano, R., & Sossa, H. (2020). PD+ SMC quadrotor control for altitude and crack recognition using
deep learning. International Journal of Control, Automation and Systems,
18(4), 834-844.
[32] Vijayalakshmi,
N., Shrinithi, R., Sanjana, V., & Sowmiya, T. (2021, March). Vehicle
Tracking and Locking System Based on GSM and GPS. In 2021 7th International
Conference on Advanced Computing and Communication Systems (ICACCS) (Vol. 1,
pp. 758-761). IEEE.
[33] Virgilio G, V. R., Sossa,
H., & Zamora, E. (2020). Vision-based blind spot warning
system by deep neural networks. In Mexican Conference on Pattern
Recognition (pp. 185-194). Springer, Cham.
[34] Weihong,
W., & Jiaoyang, T. (2020). Research on license plate recognition algorithms
based on deep learning in complex environment. IEEE Access, 8,
91661-91675.
[35] Wijaya, K.
T., Bharoto, L. Y., Purwanto, A., & Syamsuddin, E. Y. (2020). Vision-based
parking assist system with bird-eye surround vision for reverse bay parking
maneuver recommendation. In 2020 International Electronics Symposium
(IES) (pp. 102-107). IEEE.
[36] Wijnhoven,
R. G., & de With, P. H. (2011). Identity verification using computer vision
for automatic garage door opening. IEEE Transactions on Consumer
Electronics, 57(2), 906-914.
[37] Xiao, D.,
Zhang, L., Li, J., & Li, J. (2021). Robust license plate detection and
recognition with automatic rectification. Journal of Electronic Imaging,
30(1), 013002.
[38] Zade, M.
B., & Kulkarni, S. M. (2018). Auto Vehicle Speed Control System-the Review.
In 2018 Second International Conference on Inventive Communication and
Computational Technologies (ICICCT) (pp. 1556-1559). IEEE.
