Hindawi

Applied Computational Intelligence and So Computing

Volume 2020, Article ID 8535861, 7 pages
https://doi.org/10.1155/2020/8535861

Research Article
Development of Smart Plate Number Recognition
System for Fast Cars with Web Application

Olamilekan Shobayo , Ayobami Olajube, Nathan Ohere, Modupe Odusami,

and Obinna Okoyeigbo
Department of Electrical and Information Engineering, Covenant University, Canaan Land, KM 10, Idiroko,
Road, P.M.B. 1023, Ota, Ogun State, Nigeria

Correspondence should be addressed to Olamilekan Shobayo; olamilekan.shobayo@covenantuniversity.edu.ng

Received 20 September 2019; Revised 16 November 2019; Accepted 6 January 2020; Published 7 February 2020

Academic Editor: Yangming Li

Copyright © 2020 Olamilekan Shobayo et al. This is an open access article distributed under the Creative Commons Attribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.

Traffic law violation has been recognized as a major cause for road accidents in most parts of the world with majority occurring in
developing countries. Even with the presence of rules and regulations stipulated against this, violators are still on the increase. This
is due to the fact that the rules are not properly enforced by appropriate authorities in those parts of the world. Therefore, a system
needs to be designed to assist law enforcement agencies to impose these rules to improve road safety and reduce road accidents.
This work uses a Vehicle Plate Number Recognition (VNPR) system which is a real-time embedded system to automatically
recognize license plate numbers. It provides an alternative means to VPNR using an open-source library known as openCV. The
main aim of the system is to use image processing to identify vehicles violating traffic by their plate numbers. It consists of an IR
sensor for detecting the vehicle. During testing, a minimum time was set for the sensor to detect the object which was recorded by
the microprocessor. Once it was less than the set time, the camera was triggered to capture the plate number and store the image
on the Raspberry Pi. The image captured is processed by the Raspberry Pi to extract the numbers on the image. The numbers on
the capture imaged were viewed on a web page via an IP address. The system if implemented can be used to improve road safety
and control traffic of emerging smart cities. It will also be used to apply appropriate sanctions for traffic law violators.

1. Introduction The earliest systems were deployed on the A1 road and at the
Dartford Tunnel. However, it gained more recognition in the
With the increase in the number of automobiles, it has last decade due to the advancement of the digital camera and
become increasingly challenging to track them and almost the increase in computational speed [3]. The first written
impossible to identify the owners of these vehicles in case of down case of VNPR being used to solve a crime case oc-
violation of any traffic law [1]. This has led to increase in curred in November 2005, in Bradford, UK. In the early
traffic congestion, and with it comes traffic problems. Several 1990s, significant advancement in technology led to the
cases of kidnapping, hit and run, robbery, smuggling, and redesign of vehicle plate number recognition system from
on-road fatalities are continuously reported, and this is limited, highly expensive, fixed base applications to simple
because these vehicles cannot be easily recognized especially easy to install mobile ones [4]. Vehicle plate number rec-
moving at high speed [2]. This has led to the need to develop ognition system has broad applications and is not limited to
a system that can tackle these issues. Vehicle plate number traffic control. It can be used in parking; it recognizes a
recognition system was invented by the British in 1976 at the vehicle when it enters a gate and stores the information on a
police scientific development branch in the UK. Prototype database and when the vehicle is leaving it matches it up with
systems were already in full flow by 1979, and initial con- what has already been stored. It is also used in access control
tracts were awarded for mass productions and industrial use. to grant access to only vehicles of authorized personnel.
2 Applied Computational Intelligence and Soft Computing

Although vehicle plate number recognition system has been implementation of an automated plate number recognition
regularly addressed on paper, it has not been completely system using Optical Character Recognition (OCR) to in-
actualized in real-life scenarios due to certain constraints [5]. terpret information on the images of a vehicle plate number
We live in a digital age with new technologies springing forth using Raspberry Pi processor. The image captured is pro-
everyday, and as a result, only minimal human effort is cessed and verified by the Raspberry Pi processor for au-
required to get things done and life is generally simplified. thentication purposes. The proposed system then segmented
Due to the digitization of our everyday life images taken the license plate and identified each particle of the fragment.
from a camera become very useful as these images can be To get final result, the system extracts the number plate using
processed to extract important information from them [6]. open ALPR design. This result was then manually compared
Integrating vehicle plate number recognition system into with the input image. The system used was unable to detect
intelligent transport systems makes it possible to automate moving object and could not improve quality of image in the
motorway toll collection, analyze traffic, and improve law system. The system was however able to easily identify the
enforcement. The need to integrate information and tech- plate number and process the image of the number plate.
nology into all aspects of human life has led to the demand The authors in [11] implemented a system to detect over-
for processing of vehicles as a valuable resource information speeding vehicles & inform authorities in case of any vio-
communication. This is because an information system lations. The system makes use of LIDAR (Light Detection
without any form of data on it is unrealistic. There has always and Ranging) technology to check the speed of the moving
been a need to identify vehicles by their plate number in a vehicle. LIDAR is a remote sensing method that makes use of
real environment and use the information in real-life ap- light in form of pulsed laser to measure the distance to a
plications. Due to this, various techniques and vehicle target by illuminating the target with pulsed laser light and
recognition systems have been developed for various ap- using a sensor to measure the reflected pulses [12]. The
plications such as traffic control, automation, and security major drawback of the system is its high cost and the amount
[7]. of time taken to achieve it. The system was however an
effective system. The authors in [13] implemented an ALPR
2. Related Works for detecting traffic violators for promoting sustainability in
modern transport systems. This system made use of a camera
The increasing affluence of modern life has led to an increase to capture the plate number of vehicles. The image was then
in the number of user-road vehicles. This has led to an refined using different techniques such as thinning and
unprecedented level in civil problems—the problems being convolution; next OCR (Optical Character Recognition) was
vehicle identification and traffic control [8]. Due to the used to recognize the text on the number plate. The image
increasing challenge of traffic control, there arises a need to was then extracted in the form of text; the characters are then
manage traffic better. The recognition of fast-moving ve- matched with a prestored database containing details of the
hicles is an important aspect of Intelligent Transportation college or campus road users with their cell-phone number
System (ITS). ITS was developed to implement information and vehicle plate number. When a match is detected, the
and communication technologies in the field of road offender is sent a warning message on his phone number.
transport, some of which include vehicle management, The major limitation of the system was the difficulty in
traffic management as well as interfacing with other systems implementing system in larger areas like cities. The system
of transportation. A lot of researchers have tried to develop was highly accurate and cost effective as not many com-
ITS systems with different levels of success stories. The ponents were required. The authors in [14] designed a
authors in [9] designed a system to recognize plate numbers system to automatically detect number plates of vehicles in
using Python and OpenCV. The design was implemented the cases of variations in the number plate. These variations
using a real-time embedded system designed to automati- could be the location of the plate, font size on the plate, and
cally identify number plates of vehicles. The system made use various designs and text used on the number plate. The
of the python software and image processing algorithms in system made use of a preprocessing module to improve the
the OpenCV library to capture the image. It was also used in quality of the captured image. Removal of blur and noise was
preprocessing to resize the image, perform error checking, also carried out in this stage. Next, the system used plate
and convert image to grayscale. Threshold algorithms were localization to create a bounding area around the region of
used to binarize the image in order to retain the quality of the image. Then the numbers on the number plate were
image, and character segmentation was done using image extracted after which they were segmented to identify the
scissoring to scan the image and crop out the white portion region of each character on the number plate. Finally, the
by partitioning the image lines into individual characters. numbers were sent to a database with appropriate infor-
The system however was unable to sense moving vehicles mation on the owner of the vehicle. The downside of the
and had no presence of database to record information system was the several stages involved which were cum-
collected. The system is easy to use as it makes use of free- bersome and the several components required which made it
open source software applications that are easy to use and expensive. The upside of the system was the high accuracy of
also makes use of computer vision for conversion of still 98.75% recorded in number plate detection and the pro-
images to information usable by computers. The authors in vision of a database to record information collected which
[10] designed a system that automatically recognizes plate was useful for referral purposes. The author in [15] designed
number using Raspberry Pi. The system proposes the a system to identify the plate number of fast-moving vehicles
Applied Computational Intelligence and Soft Computing 3

using snapshots of precaptured images of surveillance of the camera. The plus of the system was that it was
cameras. The design made use of an estimation algorithm automated and made use of a database to compare existing
parameter known as the novel kernel parameter for plate numbers.
deblurring the plate number of the fast-moving vehicles.
Various algorithms were used to carry out sparse repre-
2.1. The Problem. Traffic laws and devices are put in place to
sentation, the angle was calculated using the genuine
monitor and control traffic, including pedestrians, motor
motion angle of the vehicle and the length of the motion
vehicle drivers, and cyclists. As is well known, there are
kernel was calculated using random transform in the
several traffic law offenders in our country today and this has
frequency domain. Finally, the image was deblurred using
led to several accident incidents without any repercussion
NBID (nonblind image deblurring) algorithm. The
being meted out. These traffic law breakers go about their
downgrade of the system was the extreme difficulty in
business freely and confidently knowing that they may never
implementing the system and the lack of a database to
be caught because the appropriate systems have not been put
record information collected. The positive side of the
in place. The resultant consequence of breaking traffic laws
system was its ability to handle motion blurred number
has led to traffic gird locks, road accidents, and even death
plate which is unrecognizable by the naked eye. The authors
when involved in a fatal accident. There is no questioning the
in [16] designed a system to recognize dirty and unclear
need for appropriate systems to check mate traffic law
vehicle number plates for real-time applications. The
breakers so as to ensure our roads are safer. The current
system was implemented to meet real-time conditions,
problem involves identifying fast-moving vehicles by their
some of which include variations in weather conditions,
plate number. It can be extremely hard to capture the image
poor lighting, different traffic situations, and high-speed
of moving vehicles in real time in such a way that the vehicle
vehicles all of which affect vehicle detection. The system
plate number is detected. The existing systems reviewed
implemented made use of several hardware platforms along
above have deployed several means to capture plate number
with robust algorithms to detect vehicle plate number.
systems. Most of them successfully captured the plate
Datasets were used from images captured from crossroads
numbers of fast-moving vehicles. The closest to this work,
in different conditions, in the day and night and other
which uses OpenCV with python, was able to detect the plate
various conditions. The system made use of plate detection
number but did not incorporate a database system to
to identify the vehicle plate number which was then seg-
identify the culprit.
mented into individual characters before character rec-
ognition was carried out. The limitation of the system was
its inability to detect moving vehicles. The benefits of the 2.2. Proposed Solution. Our proposed solution will be a
system were the high accuracy results of 98.7%, 99.2%, and novel system that uses the existing OpenCV code, written in
97.6% recorded and its numerous real-life applications. The Python but will incorporate a web page that will display the
authors in [17] implemented a system to recognize vehicle result of the saved plate number, which can be used to query
number plate using IOT (Internet of Things). The system a database for the identification of a defaulter. The database
was designed to meet changing urban requirements in the will have the plate numbers of all vehicles that will be tested
modern-day transportation system. The system proposed and queried to reveal the defaulter. The system developed
four major stages: preprocessing of the obtained image to will take a very effective and methodological approach in the
enhance the quality of the number plate, extraction of the detection of fast-moving vehicles, using cost-effective
plate number region, character segmentation to segment techniques and achieving great results. The process flow of
each character in the number plate, and character recog- the system is shown in Figures 1–5.
nition. The system also proposed the use of a novel algo-
rithm to extract the plate number region through a unique
2.2.1. Vehicle Detection. The proposed system identifies the
edge detection algorithm. The system also created a da-
moving vehicle using passive infrared sensors (PIR). Upon
tabase which contains information about the owner of
sensing the vehicle, the PIR sends an input signal to the
different vehicles which was done using IOT. However, the
Raspberry Pi which in turn triggers the USB camera.
system was unable to detect moving vehicles and could not
be used in real-life application. The system however had
provision of a database to record collected information and 2.2.2. Image Acquisition. The next step is the image ac-
was implemented using modern technology—IOT. The quisition. The Raspberry Pi which is interfaced with on
authors in [18] developed a system to identify vehicles that receiving the input signal triggers the camera to capture the
go in and out of a barrier gate parking system. The system image of the vehicle. This is quite a difficult task as it entails
made use of a real-time embedded system consisting of a capturing the image of a moving vehicle to extract infor-
Pinoir camera for image capture and a Raspberry Pi for mation in real time. The image should be captured in such a
image processing. Once the system detects a vehicle way that it contains either the front or rear view of the
approaching the barrier, it automatically reads the license vehicle with its plate number [19]. The image to be captured
plate number and compares it with an existing list and is usually in the RGB (Red, Green, and Blue) colour model.
opens the barrier if there is a match. The major short- The level of success in this stage can be affected by a number
coming of the system was the inability to capture the license of factors, some of which include system noise, blur, dis-
plate number at far distances because of the fixed position tortion, and excessive relative motion of vehicle.
4 Applied Computational Intelligence and Soft Computing

Vechicle detection using preprocessing algorithms. The algorithm converts

RGB image in 3-dimensional to 2-dimensional gray format.
Image acquisition

Image pre-processing 2.2.4. Number Plate Recognition. This is a very important

stage in the VPN system. Number plate detection searches
Number plate recognition the image taken in order to locate the specific features that
contain the number plate. The system makes use of
Character segmentation
OpenCV—Open source Computer Vision—to convert data
Character recognition from images on a camera to useful information on the
Raspberry Pi. It involves processing of real-time images to
Figure 1: Proposed design process flow. provide vision to the computer. Each frame in the image will
be processed to find the object in the image [22, 23].

Start
2.2.5. Character Segmentation. This process involves crop-
ping out the required portion of the plate number. It par-
Object dectection titions line images into individual characters; it divides an
image comprised of characters into subimages of individual
symbols. It involves isolating the image from the back-
Image capture ground in order to properly identify each text.

2.2.6. Character Recognition. This is where optical character

recognition and OpenCV are fully utilized. It involves
Was image Image not
captured? captured detecting and identifying image frames and converting them
to meaningful text in ASCII (American Standard Code for
Information Interchange).

3. System Requirements and Design Methods

Number
plate The proposed system is built on a Raspberry Pi with a USB
camera to capture a traffic scene. It makes use of a PIR
motion sensor which detects infrared energy radiating
Conversion to gray from objects (plate number) within its field of vision. The
PIR sensor sends an input signal to the Raspberry Pi which
in turn triggers the USB camera to capture the image. The
Noise removal
Raspberry Pi extracts the number plate part of the image. It
then processes the extracted part through a series of image
processing techniques to extract the numbers from the
Number plate number plate and display it on an LCD display. The
regcognition resulting data are then matched to records on a database set
up on the Raspberry Pi. The system requirement is listed
below:
End (i) Microprocessor: Raspberry Pi model B, 5 V-DC
input voltage
Figure 2: The system design flowchart. (ii) Camera: USB camera, 5 Megapixel
(iii) PIR sensor: 300 W output load
(iv) LCD Display: 16 ∗ 2-character display
2.2.3. Image Preprocessing. The image captured by the
(v) Operating system: Linux based Raspbian OS
camera needs to be processed to improve the quality of the
image. This involves background subtraction, enhancing The flowchart of the designed system is shown in the
contrast, sharpening or smoothing, and noise removal [20]. flowchart below:
It serves as a correction mechanism to take care of errors that The design of the system consists of the hardware
might have occurred during image acquisition. It entails component design and the software component design.
converting RBG image into gray colour and border en- The interaction between the two parts is shown in the
hancement for brightness [21]. To convert images in RGB to block diagram below:
gray format, each RGB component requires at least 8 bits for The system is implemented in 3 phases, which includes
their storage. The preprocessing technique is implemented the setting up of the Raspberry Pi, implementing the
Applied Computational Intelligence and Soft Computing 5

sudo apt-get update (used to download package list

Power supply
from repositories).
Camera
sudo apt-get upgrade (this installs newest version of
already installed software).
Raspberry Pi 3
sudo rpi-update (used to update firmware).
LCD screen Database For software implementation, some packages and li-
braries were installed before writing code to properly in-
terface components like the sensor. The code was developed
for the Raspberry Pi using the python programming lan-
guage. The libraries were installed using a line of command
“sudo apt-get install” on the python terminal. They include
IR sensor
the following:
Figure 3: Block diagram of the proposed system. sudo apt-get install <python-pip> (library for LCD
screen)
sudo pip install RPLCD (library for LCD screen)
sudo apt-get install <fswebcam> (library for USB
camera)
sudo apt-get install < libopencv-dev> (library for image
processing)
sudo apt-get install <numpy> (library that supports
linear algebra).
sudo apt-get install <pytesseract> (library for optical
character recognition)
In programming the Raspberry Pi, all the libraries that
were installed were first imported using the import com-
Figure 4: Designed web page for the system. mand. Then the pins connecting to the LCD screen were
specified using the CharLCD. A potentiometer was used to
calibrate the proximity range of the IR sensor so that at a
certain range, it sends an input signal to the Raspberrry Pi
which triggers the camera to capture the image. Once the
image is captured, it stores it in a created folder on the
desktop of the Pi. This is where the image processing takes
place; this is done through a sequence of operations. First of
all, the source path of the image is specified using the
img_path command. Next the image was converted from its
binary form to grayscale using the COLOR_BGR2GRAY
command. This was done to simplify the image for easy
analysis. Afterwards a noise removal algorithm introduced
Figure 5: Showing captured plate numbers.
using the scr_path + “remove_noise.png command. This was
done to smoothen the entire image. The cv2.THRESH_-
software part, and finally assembling the hardware com- BINARY,31,2 was used to further simplify the image to a
ponents of the system. While setting up the Raspberry Pi, basic form which is either black or white. After thresholding,
which is the most vital part of this work, an SD card was noise removal was carried out to further smoothen image,
provided for the Raspberry Pi since it does not have a after which a series of image processing techniques were
memory of its own. This SD card holds the Operating carried out to finally extract the actual numbers on the image
System of the Raspberry Pi. The OS used is the raspbian- and display on an LCD screen. Then the number is com-
jessie.img OS which is a variant of Debian. The pared with others on a database. Hardware components
Win32DiskImager is used to copy the OS to the SD card. were interfaced with the Raspberry Pi. For the hardware
The size of the raspbian OS is 4 GB; hence a 16 GB SD card implementation, an IR proximity sensor was used to detect
was used to provide enough space for other functionalities. the plate number. The IR sensor has 3 pins: one is connected
Once this is complete, the SD card is inserted into the to a 5 v Vcc of the Raspberry Pi, the other one is connected to
micro USB slot of the Raspberry Pi. After successfully ground, and the last one which sends the input signal to a
setting up the SD card, some commands were given to GPIO pin on the Raspberry Pi.
properly set up Raspberry Pi for use. This instruction Finally, a web page was developed to access the text
includes the following: extracted from the pictures taken by the camera over a
6 Applied Computational Intelligence and Soft Computing

Figure 6: Threshold text image. Figure 7: Noiseless text image.

As seen from the above screenshot, the module was able

network. Web programming was done using the Hyper-text
to capture different plate numbers of cars which was deemed
Markup Language (HTML) on the python IDE. An IP
to have crossed the set speed threshold, and it was able to tag
address 0.0.0.0/5000 was used on the network of the web
each one of them with a unique number, i.e., 9.0, 8.0, 12.0.
page. The web page can be accessed by anyone on the same
This serves as ways of differentiating each vehicle from the
network as the Raspberry Pi. The diagram below shows a
other so it can easily be traced on the database. The saving
sample of the text from the designed web page.
sequence could also be observed from the screenshots shown
below.
4. Testing and Result As shown in Figure 6, the text received from the camera
is in the threshold form, i.e., it is susceptible to noise and
After successful assemblage of the hardware parts and the other kinds of interference. The Raspberry Pi is configured to
configuration of the software components, the functionality perform filtering on the image by removing the noise
of the system was tested on a built model. The IR sensor was components as shown in Figure 7. The image in Figure 7 is
used to detect the moving cars. Once detected, the camera made available to the web page developed for the system,
was triggered to capture the image of the plate number. The which is accessible to the database that holds the accurate
system was tested on a simulated prototype road, and the information of the car owner.
calibration was to detect a speed limit of 40 centimeter/hour.
Cars were made to pass on this road with varying speeds.
5. Conclusion
Out of the cars that passed, the system was able to detect 3
cars moving with speeds more than the stipulated limit. To In this work, a highly efficient, economical, and VRPN
detect these fast-moving cars, 3 PIR motion sensors were system was developed. This system uses smart IR sensor to
attached to segments of the road in order to send signal to detect moving objects, camera to capture the image, extract
the Raspberry Pi to trigger the USB Camera. The PIR sensors the text from the image, and save the text on a web page. The
were placed 40 centimeters apart, i.e., 20 centimeters be- major component selected to do the main work in the system
tween each sensor. The sensors were programmed such that is the Raspberry Pi. OpenCV was used together with python
when a fast car approaches the first sensor, the PIR cannot programming, for the character segmentation and recog-
trigger the camera in 10 second (this is also scaled by a value nition. This was configured on the Raspberry Pi, including
of 10 to mark the speed limit), and also the second PIR, then the required library that is required to make the hardware
the third PIR will automatically trigger the USB camera to components of the system to work with the Raspberry Pi. As
take pictures of the car as it is assumed to be overspeeding. shown in the results, the developed system was able to
Images of the cars that the first and second PIR sensors deliver a clear and readable text on a web page which can be
triggered the camera for were discarded as it is assumed that used to query a database. Due to the calibration of the IR
these cars were not overspeeding. Only images triggered by sensor, it is able to detect fast-moving cars and also able to
the third PIR were processed. The camera was placed in such log different cars at different times using a tag for each data it
a way that the rear of the car will be captured so that its plate receives and having a unique saving sequence. The system is
number can be captured and verified with an existing da- by far one of the cheapest means for the actualization of
tabase. After this was complete, the captured image was traffic management in a smart city.
made to undergo image processing and optical character
recognition. This is made possible by the OpenCV codes Data Availability
written with Python. Once the text was extracted, it was
displayed on a web page. The results obtained are as shown The data used to support the findings of this study are
below. available from the corresponding author upon request.
Applied Computational Intelligence and Soft Computing 7

Conflicts of Interest [14] S. Shah, N. Rathod, P. K. Saini, V. Patel, H. Rajput, and

P. Sheth, “Automated Indian vehicle number plate detection,”
The authors declare that they have no conflicts of interest. in Soft Computing: Theories and Applications, pp. 453–461,
Springer, Berlin, Germany, 2019.
[15] N. Bolaj and G. Padalkar, “The license plate identification of
Acknowledgments fast moving vehicles,” in Proceedings of the 2017 International
Conference on Computing, Communication, Control and
This research was funded by the Covenant University Center Automation (ICCUBEA), pp. 1–5, Pune, India, August 2017.
for Research, Innovation, and Discovery (CUCRID). [16] R. Panahi and I. Gholampour, “Accurate detection and rec-
ognition of dirty vehicle plate numbers for high-speed ap-
plications,” IEEE Transactions on Intelligent Transportation
References Systems, vol. 18, no. 4, pp. 767–779, 2016.
[1] D. Mitra and S. Banerjee, “Automatic number plate recog- [17] K. Tejas, K. A. Reddy, D. P. Reddy, K. Bharath, R. Karthik, and
nition system: a histogram based approach,” IOSR Journal of M. R. Kumar, “Efficient license plate recognition system with
Electrical and Electronics Engineering, vol. 11, pp. 26–32, 2016. smarter Interpretation through IoT,” in Soft Computing for
[2] A. Goyal and R. Bhatia, “Various techniques for number plate Problem Solving, pp. 207–220, Springer, Berlin, Germany,
recognition-a review,” International Journal of Computer 2019.
Applications, vol. 143, 2016. [18] E. R. Buhus, D. Timis, and A. Apatean, “Automatic parking
[3] B. Singh, M. Kaur, D. Singh, and G. Singh, “Automatic access using openalpr on raspberry pi3,” Acta Technica
number plate recognition system by character position Napocensis, vol. 57, p. 10, 2016.
method,” International Journal of Computational Vision and [19] S. M. Mutua, An Automatic Number Plate Recognition System
Robotics, vol. 6, no. 1-2, pp. 94–112, 2016. for Car Park Management, Strathmore University, Nairobi,
[4] M. T. Qadri and M. Asif, “Automatic number plate recog- Kenya, 2016.
nition system for vehicle identification using optical character [20] NOAA, LIDAR–Light Detection Ranging—is a Remote Sensing
recognition,” in Proceedings of the 2009 International Con- Method used to Examine the Surface of the Earth, NOAA,
ference on Education Technology and Computer, pp. 335–338, Silver Spring, MD, USA, 2013.
Singapore, April 2009. [21] D. Y. Gaikwad and P. B. Borole, “A review paper on automatic
[5] R. Laroca, E. Severo, L. A. Zanlorensi et al., “A robust real- number plate recognition (ANPR) system,” International
time automatic license plate recognition based on the YOLO Journal of Innovative Research in Advanced Engineering
detector,” in Proceedings of the 2018 International Joint (IJIRAE), vol. 1, 2014.
Conference on Neural Networks (IJCNN), pp. 1–10, Rio de [22] O. Abayomi-Alli, M. Odusami, D. Ojinaka et al., “Smart-Solar
Janeiro, Brazil, July 2018. Irrigation System (SMIS) for Sustainable Agriculture,” in
[6] P. Bhogale, A. Save, V. Jain, and S. Parekh, “Vehicle license Proceedings of the International Conference on Applied In-
plate detection and recognition system,” International Journal formatics, pp. 198–212, Medan, Indonesia, September 2018.
of Computer Applications, vol. 137, no. 9, pp. 31–34, 2016. [23] K. Okokpujie, E. Noma-Osaghae, S. John, K.-A. Grace, and
[7] G. Sharma, “Performance analysis of vehicle number plate I. Okokpujie, “A face recognition attendance system with
recognition system using template matching techniques,” GSM notification,” in Proceedings of the 2017 IEEE 3rd In-
Journal of Information Technology & Software Engineering, ternational Conference on Electro-Technology for National
vol. 8, no. 2, 2018. Development (NIGERCON), pp. 239–244, Owerri, Nigeria,
[8] E. Council, “Directive 2010/31/EU of the European parlia- November 2017.
ment and of the council of 19 may, 2010 on the energy
performance of buildings,” Official Journal of the European
Union, vol. 153, pp. 13–35, 2010.
[9] K. Sajjad, Automatic License Plate Recognition Using Python
and Opencv, Department of Computer Science and Engi-
neering, MES College of Engineering, Kuttippuram, Kerala,
2010.
[10] A. Kumthekar, M. S. Owhal, M. S. Supekar, and M. B. Tupe,
“Recognition of Vehicle Number Plate Using Raspberry Pi,”
International Research Journal of Engineering and Technology,
vol. 5, no. 4, pp. 391–394, 2018.
[11] J. Muñoz, M. Craft, M. Ahmadian, and S. Wrobel, “Multi-
function LIDAR sensors for non-contact speed measurement
in rail vehicles: Part I—system installation and imple-
mentation,” in Proceedings of the 2013 Joint Rail Conference,
Philadelphia, PA, USA, April 2013.
[12] S.-L. Chang, L.-S. Chen, Y.-C. Chung, and S.-W. Chen,
“Automatic license plate recognition,” IEEE Transactions on
Intelligent Transportation Systems, vol. 5, no. 1, pp. 42–53,
2004.
[13] P. Agarwal, K. Chopra, M. Kashif, and V. Kumari, “Imple-
menting ALPR for detection of traffic violations: a step to-
wards sustainability,” Procedia Computer Science, vol. 132,
pp. 738–743, 2018.