Volume 5, Issue 7, July – 2020 International Journal of Innovative Science and Research Technology

ISSN No:-2456-2165

Improvised Guard for Next Level Security

Automated Vehicle Security System using Artificial Intelligence and
Convolutional Neural Network

Joel M John1, Noel Phillip Issac1, Jerin Thomas1 , Syamraj B S2

Subin Alexander1 2
Assistant Professor
Department of Computer Science and Engineering, Department of Computer Science and Engineering,
St Thomas College of Engineering and Technology St Thomas College of Engineering and Technology
Chengannur, India Chengannur, India

Abstract:- This paper details fully automated vehicle vehicle model, color, make, number plate recognition
security system involving vehicle model, make detection, differentiating a genuine or fake number plate by
driver face recognition and parking system guided by a verification with MVD(Motor Vehicle Department)
virtual assistant. The core technology of the system is database. This system enhances apt Vehicle security and
built using a sequence of deep Convolutional Neural requires no manual control as it is fully automated
Networks (CNNs). This system performs face functional system monitored and controlled by the Artificial
recognition of the driver and vehicle model, make Intelligent system.
detection and permit access by opening barrier gate.
This allows bigger organizations to control and monitor II. LITERATURE SURVEY
vehicle traffic as well as gain user data for security
purpose. For quantitive analysis, we show that our  Number Plate Recognition for Use in Different
system outperforms the leading vehicle security system. Countries Using and Improved Segmentation
Proposed paper project website is also available at Automatic Number Plate Recognition (ANPR) is a
http://www.astound.ga/igns. real time embedded system which identifies the
characters directly from the image of the license plate. It is
Keywords:- Virtual Assistant, Recognition, Authorization, an active area of research. ANPR systems are very useful to
Validation, Vehicle, User interaction. the law enforcement agencies as the need for Radio
Frequency Identification tags and similar equipments are
I. INTRODUCTION minimized. Since number plate guidelines are not strictly
practiced everywhere, it often becomes difficult to
Recently CCTV security systems is used in numerous correctly identify the non-standard number plate
areas, industries, entry restricted areas or by government characters. In this paper we try to address this problem
including ANPR(Automatic Number Plate Recognition) for of ANPR by using a pixel based segmentation
vehicles, Face identification etc.. ANPR Security Systems algorithm of the alphanumeric characters in the license
(Automatic Number Plate Recognition) can be used to store plate. The non-adherence of the system to any particular
the images captured, as well as the text from the number country-specific standard & fonts effectively means that
plate. It is also able to store a photograph of the driver. With this system can be used in many different countries – a
the advent and enhancements of deep CNNs and cheaper, feature which can be especially useful for trans- border
faster processing hardware, we need to take a fresh look at traffic e.g. use in country borders etc.
the problem. Advances in the design of CNNs have resulted
in significant increases in performance accuracies for many  A Study of Car Park Control System Using Optical
tasks. In this work, we harness the power of CNNs in an Character Recognition
end-to-end system capable of detecting and recognizing This paper presents the study and design of car park
license plates with low error rates. We present a system that control system using optical character recognition (OCR)
is robust to variations in conditions (camera movement, devices. The system uses client server environment. The
camera angle, lighting, occlusion, etc) and license plate administrator will monitor the system and the database from
templates (size, designs, formats, etc). But the existing the server side. Furthermore the parking information will be
system needs much more relations, tight security based displayed static based on the database shared by the server.
information technologies and additional automated features Server application and database will be stored in the
for easy access and user interactions .That’s where this server. The result shows the system is capable to save
project comes in handy, IGNS (Improvised Guard for Next log record that will ease tracking parking user, updating user
Level Security) system provides entirely automated vehicle and parking credit database as well as monitoring
security by a virtual assistant involving user interactions by availability of parking spaces.
clearly recognizing the driver with face recognition and

IJISRT20JUL121 www.ijisrt.com 84
Volume 5, Issue 7, July – 2020 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
 Prevent Crime by Face Recognition  AIDA is powered by speech recognition system which
Face recognition is currently being used to precisely with an accuracy of 95% can recognize and
instantly identify when known shoplifters, organized understand speech.
retail criminals or people with a history of fraud enter  This provides way for interaction of the system with the
retail establishments. Photographs of individuals can be driver for accessing information such as name, mobile
matched against large databases of criminals so that loss number for future security purposes.
prevention and retail security professionals can be instantly
notified when a shopper enters a store that prevents a
threat. Face recognition systems are already radically
reducing retail crime.

III. PROPOSED SYSTEM

IGNS (Improvised Guard for Next Level Security)

system provides apt security by a virtual assistant involving
user interactions by clearly recognizing the driver with face-
id and vehicle model, color, make, number plate
differentiating a genuine or fake number plate by
comparison with MVD(Motor Vehicle Department)
database. The contributions of this system are summarized
below.
 Face recognition involving face identification of the
driver
 Vehicle model, make, color detection Fig 2:- user interface of virtual assistant
 User authentication, involving validation of number
plate and driver details such as name, mobile no. B. Recognition
 System action involving access or denial  Face Recognition
Face recognition systems use computer algorithms to
pick out specific, distinctive details about a person’s face.
These details, such as distance between the eyes or shape of
the chin, are then converted into a mathematical
representation and compared to data on other faces
collected in a face recognition database. Based on the
information received from the face recognition the driver
can be identified as an existing user or a unknown(new
user).

Fig 1:- Overview of the proposed system

IGNS security system strives for automation hence the

entire system control is based on the guidance of an Fig 3:-a) Recognized Driver b) Unknown Driver
Artificial intelligence or Virtual Assistant named A. I. D. A
(Advanced Intelligence in Decision and Action) which  Vehicle Recognition
enhances interaction with the driver. Make, model and color recognition (MMCR) of
vehicles is one of great interest in several applications such
A. Virtual Assistant as law-enforcement, driver assistance, surveillance and
 Once Recognition is initiated by user, then AIDA traffic monitoring. The IGNS system detects vehicle plate,
undertakes the system control and communicates with model and make in order to validate the authenticity of the
the user and extracts information of the driver through vehicle with the number plate from the MVD.
voice recognition such as driver name and mobile
number.
 Meanwhile the camera1 and camera 2 capture images of
the face of driver and vehicle respectively

IJISRT20JUL121 www.ijisrt.com 85
Volume 5, Issue 7, July – 2020 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
driver face is existing user then the driver and the vehicle
will be granted access only if the number plate is genuine.
On the other hand if the driver face is recognized as
unknown then the system will prompt for user registration
followed by saving the driver name, mobile number and
face id for future recognition and proceed to number plate
verification.

 Genuine Number plate

The system scans the number plate and initiates
Fig 4:- Vehicle Recognition verification with the MVD database . Henceforth changes
found different in vehicle color, make from the actual
C. Authorization MVD database can be identified easily and the number
Authorization is a function of providing access or plate will be blacklisted and access will be denied.
privilege to the user based on the following factors.
1)Existing user 2)Genuine Number plate  Parking Management
If the system verified number plate is genuine then the
 Existing user access is granted to the vehicle and an welcome SMS is
Based on the information received from the face sent assigning a parking slot for parking. Parking system
recognition the driver can be identified as an existing user assigns parking slot with respect to the vehicle model.
or a unknown(new user) as shown in Fig 3a and 3b. If the

IV. SYSTEM ARCHITECTURE

The given is the conceptual architectural diagram of the IGNS system.

Fig 5:- System Architecture of IGNS security system

IJISRT20JUL121 www.ijisrt.com 86
Volume 5, Issue 7, July – 2020 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
 Phase 1: Once the system is initiated to start recognition The IGNS system allows admin to control and
the virtual assistant AIDA takes control by taking monitor the vehicles. Figure 6 represents admin view of
pictures of the vehicle as well the driver face. This was IGNS system
the first user interaction phase.
 Phase 2:The next is the recognition phase where the face
and vehicle picture collected from the system is detected,
transformed and cropped and feed to deep neural
network. Here the system performs recognition of driver
and vehicle recognition such as number plate, make, and
color.
 Phase 3:The third phase is authorization where the
information received from the recognition are strictly
validated with the system database containing
information of all users as well as MVD database. Here
the system can identify user and detect fake number
plates. Based on the results the system will conclude as
authorized or unauthorized vehicle and proceed to final
Action.
 Phase 5:The Final is Action phase where the user will
receive an welcome sms and the gate will be opened for Fig 6:- Admin View of IGNS system
the driver to proceed if its an authorized user or else
otherwise. The IGNS system has read access over the MVD
hence it helps the system to identify fake number plate of
A. System Requirements the vehicle. The figure 7 represents the view of the MVD
database.
 Minimum Hardware Requirements
 CPU: Core i5
 GPU: Geforce GTX 750 Ti
 RAM: 8GB
 Hard Disk: 128GB
 Arduino Uno

 Software Requirements
 OS: Windows
 Coding Language: Python 3 or higher, C Fig 7:- Motor Vehicle Department Database
 IDE: Pycharm 2019 or higher, Arduino 1.0
VI. CONCLUSION AND FUTURE SCOPE
V. RESULTS AND DISCUSSION
In this paper we presented an end to end autonomous
For a fully investigation of the proposed methods, the advanced vehicle security system for vehicles recognizing
proposed system considers the following aspects: make, model, color recognition as well as driver face
recognition. The approach to the design and
 Effectiveness: The studies evaluate the detection implementation of deep neural networks and a sizable
performance of the trained model and comparison dataset for training allow to label vehicles in real time with
methods in terms of Accuracy, Recall and Precision high degrees of accuracy. With the additional features of
 Efficiency: The studies evaluate efficiency of the face recognition of drivers, validation of number plates
methods by comparing the CPU time of training each powered by A.I.D.A the IGNS system proposes fully
model. All experiments are performed on an x64 automated functional security system that initiates a tight
machine with 2.80 GHz Intel Core i5 CPU and 16 GB security.
RAM.
A. Advantages and Limitations
The IGNS vehicle security system performs
authorization of user involving:  Advantages
 Automated Vitual Assistant system for interaction with
 Speech Recognition: A.I.D.A Recognizing speech from user.
driver and exchange information.  No need of an actual security guard
 Face id: Recognizing driver face for identification  Fully autonomous security
 Vehicle Recognition: Recognizing driver vehicle details  Reduces fraudulent activities of number plates
 Automated system for detecting vehicles models
 Automated Parking slots via sms

IJISRT20JUL121 www.ijisrt.com 87
Volume 5, Issue 7, July – 2020 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
 Limitations [7]. Du, S., Ibrahim, M., Shehata, M., Member,
 New user registration may consume some time S., Badawy, W.: Automatic license plate
 Number plate recognition may consume more time on recognition (alpr): A state-of-the-art review.
difficult fonts In: IEEE Transactions on Cir- cuits and
 Weather condition may affect the clarity of pictures Systems for Video Technology. Volume 23.
captured by camera (2013)
 Heavy Noise during speech recognition may result error [8]. Cheang, T.K., Chong, Y.S., Tay, Y.H.: Segmentation-
values free vehicle license plate recognition using convnet-
rnn. (2017)
B. Future Applications [9]. Yuan, Y., Zou, W., Zhao, Y., Wang, X., Hu, X.,
Komodakis, N.: A robust and efficient approach to
 Road Safety: Features of IGNS system such as license plate detection. In: IEEE Transactions on
automated number plate recognition system combined Image Processing. Volume 26. (2017)
with face recognition and vehicle detection can be [10]. https://www.sighthound.com/
upgraded to new level of security for road safety [11]. https://www.pyimagesearch.com/
management system for the government. The system
can be used to understand and analyze daily traffic flow.

 Vehicle Tracking: Since the Proposed system uses

number plate for recognition it is possible to track the
vehicle anywhere with the same plate.

 High Security: The system can work efficiently in areas

which restrict human interactions such as military base.

 Monitor Activity: The system can be used to monitor

activity records of the driver and vehicle which would
stand as a vital information for investigation authorities.

 User Tracking: The system enables face identification

for security purpose. Hence can play a vital role in
tracking a user.

REFERENCES

[1]. Espresso: A Fast End-to-End Neural Speech

Recognition Toolkit Yiming Wang ; Tongfei Chen ;
Hainan Xu ; Shuoyang Ding ; Hang Lv ; Yiwen Shao ;
Nanyun Peng ; Lei Xie ; Shinji Watanabe ; Sanjeev
Khudanpur 2019 IEEE Automatic Speech Recognition
and Understanding Workshop (ASRU)
[2]. Sochor, J., Herout, A., Havel., J.: Boxcars: 3d boxes as
cnn input for improved _ne-grained vehicle
recognition. In: CVPR. (2016)
[3]. Hsieh, J.W., Chen, L.C., Chen, D.Y.: Symmetrical surf
and its applications to vehicle detection and vehicle
make and model recognition. In: IEEE Transactions on
intelligent transportation systems. (2014)
[4]. Gu, H.Z., Lee., S.Y.: Car model recognition by
utilizing symmetric property to overcome severe pose
variation. In: Machine vision and applications. (2013)
[5]. Yang, Linjie, e.a.: A large-scale car dataset for _ne-
grained categorization and veri_cation. In:
Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition. (2015)
[6]. Lin, T.Y., RoyChowdhury, A., Maji., S.: Bilinear cnn
models for _ne-grained visual recognition. In:
Proceedings of the IEEE International Conference on
Computer Vision. (2015)

IJISRT20JUL121 www.ijisrt.com 88