AUTOMATIC SLIDING GATE CONTROL SYSTEM USING

MACHINE LEARNING AND COMPUTER VISION

This project report is submitted to

Yeshwantrao Chavan College of Engineering

(An Autonomous Institution Affiliated to Rashtrasant Tukadoji Maharaj Nagpur University)

In partial fulfillment of the requirement

For the award of the degree

Of

Bachelor of Engineering in Electronics and Telecommunication Engineering

By

Kashmira Ghodkhande
Anadi Vyas
Sushrut Pantaone
Kushank Gokhale
Under the guidance of
Prof. Yogesh Kale (Guide)
Dr. Abhay Deshpande(Co-Guide)

DEPARTMENT OF ELECTRONICS AND TELECOMMUNICATION ENGINEERING

Nagar Yuwak Shikshan Sanstha’s

YESHWANTRAO CHAVAN COLLEGE OF ENGINEERING,

(An Autonomous Institution Affiliated to Rashtrasant Tukadoji Maharaj Nagpur University, Nagpur)

NAGPUR – 441 110

2023-24

i
 CERTIFICATE OF APPROVAL

Certified that the project report entitled “AUTOMATIC SLIDING GATE CONTROL
SYSTEM USING MACHINE LEARNING AND COMPUTER VISION “ has been
successfully completed by KUSHANK GOKHALE,KASHMIRA GHODKHANDE,
ANADI VYAS, SUSHRUT PANTAONE under the guidance of PROF. YOGESH KALE in
recognition to the partial fulfillment for the award of the degree of Bachelor of Engineering in
Electronics and Telecommunication Engineering, Yeshwantrao Chavan College of
Engineering (An Autonomous Institution Affiliated to Rashtrasant Tukadoji Maharaj
Nagpur University).

Signature Signature Signature

Prof. Y. S. Kale Dr. Abhay Deshpande Dr. M. S. Narlawar
(Guide) (Co-guide) (HOD, ETC Dept.)

Signature of External Examiner:

Name:
Date of Examination:

ii
 DECLARATION

We declare that

a. The work contained in this project has been done by me under the guidance of my
supervisors.
b. The work has not been submitted to any other Institute for any degree or diploma.
c. I have followed the guidelines provided by the Institute in preparing the project report.
d. I have confirmed the norms and guidelines given in the Ethical Code of Conduct of the
Institute.
e. Whenever I have used materials (data, theoretical analysis, figures, and text) from other
sources, I have given due credit to them by citing them in the text of the report and
giving their details in the references. Further, I have taken permission from the
copyright owners of the sources, whenever necessary.

Signature of Students

1) Kushank Gokhale

2) Kashmira Ghodkhande

3) Anadi Vyas

4) Sushrut Pantaone

iii
 ACKNOWLEDGEMENT

We avail this opportunity to extend my hearty indebtedness to my project guides

PROF. Y. S. KALE and Dr. AB H AY D E S H P ANDE , Department of
Electronics and Telecommunication Engineering, for their valuable guidance, constant
encouragement and kind help at different stages for the execution of this work, for his
ever encouraging and moral support.

We also express our sincere gratitude to Principal DR. U. P. WAGHE and DR. M. S.
NARLAWAR, Head of the Department, Electronics and Telecommunication
Engineering, for providing valuable departmental facilities.

We would like to thank PROF. S. S. CHIWANDE (Project Coordinator) and all staff
members of the Electronics Department for extending the facilities without which the
project would not have been a success.

We sincerely thank all academic and non- teaching staff in YESHWANTRAO

CHAVHAN COLLEGE OF ENGINEERING, Nagpur who helped me.
Our sincere thanks to the author whose work I have consulted and quoted in this work.

iv
TABLE OF CONTENTS:

CONTENTS PAGE NO
Title Page i

Certificate of Approval ii
Declaration iii

Acknowledgement iv
Table of Content v - vi

List of Figures vi

Abstract vii
Chapter 1: Introduction 1
1.1 Overview
2
1.2 Literature Survey
3
1.3 Problem Statement
4
1.4 Thesis Objectives
4
1.5Thesis Organization
5

Chapter 2: Review of Literature 6

2.1 Review of Literature
7–9

Chapter 3: Work Done 10

3.1 Tool used
11
3.2 Processes followed
11 – 13
3.3 Material Used
13 – 16
3.4 Costing
17
Chapter 4: Results & Discussion
18
4.1 Result
19-21
Chapter 5: Summary & Conclusion
22
5.1 Summary
23
5.2 Conclusion & Societal Relevance
23
5.3 Future Scope
24

v
 References
25-26
Societal relevance
27
Co-Po Mapping Table
28

LIST OF FIGURES:

FIGURE PAGE NO

Block Diagram 12

Schematic diagram 12
Aluminum pipe and Angle 13

Rack and Pinion gear 13

DC Geared motor 13

IR Sensor 14
12V DC Adaptor 14

Pushbutton switch 14
L298N 14
Raspberry Pi and Pi camera 16

Implemented system’s output 19

Implemented Output 20

Initial face recognition Simulation result 20

GrayScale Conversion 21

Detected No. plate 21

Final Detected output 21

vi
Abstract
Most people use keys, security cards, passwords, or patterns to unlock doors in order
to maintain security. The goal of this research is to help people use facial detection
to increase the entrance security of important locations. The complex
multidimensional structure of the face requires the application of strong
computational methods. Face detection, sometimes referred to as facial recognition,
is a computerized method that recognizes and verifies human faces in gathered
photographs by utilizing Computer Vision (CV) and Machine Learning (ML)—two
specializations inside Artificial Intelligence (AI). The microcontroller is configured
such that the door opens automatically for the authorized person. Conversely, the
alert will sound to notify the unidentified individual. This is only for security's
purposes. In order to validate our idea, we built a prototype, and this study piece
outlines the team's fundamental workflow.

vii
 CHAPTER 1
INTRODUCTION

1
 1.1 OVERVIEW
These days, it's common practice to use biometric traits for computerized personal
identification in authentication systems rather than chips, codes, or patterns. Utilizing
specialist tools like a fingerprint scanner, palm print scanner, or genomic analysis software,
the complete fingerprint data must be obtained. Moreover, in the intentional sampling
phase, the target objects ought to be in close proximity to the necessary electronics. Face
detection is the first stage in the facial recognition system. Face detection's entire
functionality is impacted by its dependability. Face detection is limited to identifying the
visual content of a photo without taking into account the background of the image.

With five possibilities, this proposed system provides comprehensive electronics

security and lessens the user's reliance on repeatedly opening and closing the sliding gate.
Since closed-circuit television (CCTV) is primarily a vigilance system rather than a
security system, most people who install it for security reasons find that their goal remains
unfulfilled. With this suggested system, your main entrance gate will have full security and
full user control over opening and closing, allowing the user to operate the main sliding
gate with ease. This proposed system's main objective is to enable users to operate the main
sliding gate from anywhere in the world using a mobile device, while simultaneously
lowering the

The primary contribution of this suggested system is the integration of Internet of

Things (IoT), image processing, and real-time processing with the manual sliding main gate
already in use. The primary sliding gate is used more frequently thanks to these next-generation
technologies because the usage of all the manual sliding gates that are currently in place is
inadequate; frequently, the gate is not fully open, and users typically park their two- and four-
wheelers outside of the main sliding gate. The suggested vehicular entry arrangement makes
parking easier for a lot of people.

2
 1.2 LITERATURE SURVEY

Proposed method for face recognition

1) Face Detection

One of the most popular uses of computer vision (CV) for security applications is face
detection. Several techniques for detecting facial features have been introduced in the past
ten years. Convolutional neural networks (CNNs) and machine learning have achieved
remarkable results in powering extremely accurate face detection resolutions in recent
years. The position and size of a humanoid face in digital photos can be controlled using
a computer technology called face detection; however, the recommended method
concentrates on the image itself rather than the location. Face detection, which combines
AI, ML, and CV, is the initial step in face recognition, according to P. Viola and M. J.
Jones.

The input picture is first converted to grayscale since data processing is much reduced
and it is much easier to operate in a single image plane than a three-dimensional colorful
image without losing vital information. The Haar Cascade Classifier is used to identify
faces. This procedure is quicker than previous methods and produces more accurate
findings.

2) Feature Extraction

For face recognition, N. Depak Shyam and S. Shanthi utilized the LBPH (Local Binary Patterns
Histograms) algorithm. The main reason for selecting this methodology in our system was its
real-time face detection capability without any need for specific scaling in image size.
Moreover, it can distinguish both front and side faces. It divides the picture into cells, with each
cell containing pixels that are converted to a binary lighting setup. It will divide the picture into
numerous cells and save them as binary standards.

3
 1.3 PROBLEM STATEMENT

❏ If a person wants to cross the gate he/she needs to first park the vehicle and then
slide it, which is rather time-consuming and requires human effort as well.

❏ Security is the most significant element we should have in our home, it gets
compromised whenever any unknown individual attempts to barge in.

❏ Dependency of a Security Guard for opening and closing the gate.

❏ Maintenance of the sliding gate.

❏ Risks of accidents by manual operation.

1.4 THESIS OBJECTIVE

A facial recognition and license plate detection sliding gate for security reasons is designed
to improve the security of a limited area by validating the identities of persons and vehicles
attempting to enter.

The face recognition system analyzes facial traits to identify and authenticate individuals'
identities using modern algorithms. This helps to prevent unauthorized access by allowing
only authorized persons to enter.

The license plate detection system, on the other hand, recognises and scans the license
plates of cars approaching the gate before comparing them to a database of authorized
vehicles.

The sliding gate, by combining these two technologies, may effectively limit entry to a
confined area, ensuring that only authorized individuals and vehicles enter.

4
 1.5 THESIS ORGANIZATION

The following is how the thesis is structured:

Chapter 1 is the official introduction to the thesis, which provides our rationale
for commencing this thesis as well as our goals and objectives for it.

Chapter 2 is a survey of the literature, which includes current understanding and

work on this issue. It also contains all theoretical and methodological contributions
to this thesis.

Chapter 3 focuses on our suggested model for this thesis, as well as the workflow
that we followed throughout.

The final findings of our tests and data analysis are presented in Chapter 4.

Chapter 5 is the conclusion, and it offers a summary of our thesis, as well as

existing constraints, future plans, and further information.

5
 CHAPTER 2
LITERATURE REVIEW

6
2.1 REVIEW OF LITERATURE

[1] R. Chen In Image Vision Computation, vol. 87, pp. 47–56, 2019, R. Chen, "Automatic License
Plate Recognition via sliding-window darknet-YOLO deep learning,"

In this research, they address the automotive license plate detection problem using a You Only Look
Once (YOLO)-darknet deep learning system. In this study, we use YOLO's seven convolutional layers
to identify a single class. For detection, a sliding-window method is employed. Finding Taiwanese
license plates is the aim. They made use of a six-digit license plate number dataset from AOLP.

[2] "Number Plate Recognition System for Toll Collection," K. Bhosale, J. Jadav, S. Kalyankar,
and R. Bhambare, International Journal of Emerging Technology and Advanced Engineering, vol.
4, (4), pp. 729-732, 2014

In order to improve convenience and security at the entrance to all important locations that need protection
and security, the most reliable methods of vehicle license plate detection and automatic gate control
systems were reviewed in this article. At the entry gate, the system will be able to detect license plates on
cars and decide whether or not to allow vehicles within. The gate will work automatically, requiring no
human intervention. The system consists of a Raspberry Pi and a video camera that captures and processes
video frames containing an image of the license plate of the car. The proposed system was developed using
optical character recognition (OCR) and Python.

[3] "Multi-view face detection using deep convolutional neural networks," S. S. Farfade, M. J.
Saberian, and L. Li, Proceedings of the 5th ACM on International Conference on Multimedia Retrieval,
2015, pp. 643-650.

In this study, they introduce Deep Dense Face Detector, a technique that recognizes faces in several
orientations with a single deep convolutional neural network-based model and does not require
landmark annotation. Unlike other existing deep learning object recognition techniques, the
recommended solution does not require SVM classifiers, bounding-box regression, or segmentation,
making it easy to apply. Additionally, we looked at the proposed face detector's scores for faces in
different orientations and found that: 1) the suggested approach can detect faces from a variety of angles
and can manage occlusion to some degree; and 2) there seems to be a relationship between the proposed
face detector's scores and the distribution of positive examples in the training set.

[4] P. Viola and M. J. Jones, "Robust real-time face detection," International Journal of
Computer Vision, vol. 57, (2), 2004; pp. 137–154

This work provides a face detection framework that achieves high detection rates and fast photo analysis.
The first is the introduction of a new picture representation called the "Integral Image," which makes it
possible to quickly calculate the features of our detector. The second is a simple and effective classifier that
selects a limited number of important visual attributes from a vast array of potential features using the
AdaBoost learning algorithm. The third contribution is a way to combine classifiers in a "cascade" fashion,
which enables one to quickly remove background portions of an image while allocating more processing
power to regions that might represent faces.

7
[5] Hteik Htar Lwin, Aung Soe Khaing, Hla Myo Tun, “Automatic Door Access System Using
Face Recognition”, INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY
RESEARCH VOLUME 4, ISSUE 06, JUNE 2015 ISSN 2277-8616.

Tun, Hteik Htar Lwin, Aung Soe Khaing, and Hla Myo Tun proposed using MATLAB to execute
the facial recognition modal and direct the flow of data generated by cameras and sensors through
a computer in order to construct an Automatic Door Access System.

[6] K. Vikram and S. Padmavathi, "Facial parts detection using Viola Jones algorithm," 2017
4th International Conference on Advanced Computing and Communication Systems (ICACCS),
2017, pp. 1-4, doi:10.1109/ICACCS.2017.8014636.

The primary goal is to create a system that can identify and detect the textures of various body parts
in an image or a video. The different parameters of facial features are linked with the estimation
parameters of the human body components. This has other practical uses in the form of facial
recognition for online tests, determining an individual's gender and age, and much more.

[7] Neetu Saini, zukhwinder Kaur, Hari Singh, A Review: Face Detection Methods and
Algorithms, International Journal of Engineering Research & Technology (IJERT), ISSN: 2278-
0181, 2 (6), June – 2013.

Facial emotions and/or face recognition require the ability to locate and track human faces. The system has
to use a camera and frame grabber to take an image, process it, look for key elements in it, and then use
those features to locate the face.

[8] N. Dileep kumar and S. Shanthi, “Automatic Gate using Face Recognition Technique using
HAAR Cascade Algorithm”, International Journal of Engineering and Advanced Technology
(IJEAT), vol. 9, no. 3, pp. 1302–1305, Feb. 2020, Doi: 10.35940/ijeat.C5195.029320.

A great deal of effort has been done in the field of security systems. Facial recognition technology
is used in this Automatic Sliding Gate to save facial data in a database. The Raspberry Pi was used
to process the data. The haar cascade algorithm has been applied in this. Compared to the Fisher
Face, Eigenface approach, this would yield results that are more accurate. This will capture
numerous photos from various perspectives and verify each image at the moment of facial
recognition.

[9] R. Baran, T. Rusc and P. Fornalski, "A smart camera for the surveillance of vehicles in
intelligent transportation systems," Multimedia Tools Appl, vol. 75, (17), pp. 10471-10493,
2016.

The paper details a smart camera meant for use in intelligent transportation systems for law enforcement
and security purposes. First, the background is provided in the form of a survey of scholarly literature.
The next sections provide a detailed explanation and exploration of the components of the smart camera,
including how they can be used to automatically identify and recognize specific properties of cars as
well as other aspects of system efficiency. Smart features including make and model recognition
(MMR), license plate recognition (LPR), and color recognition (CR) are among the system's main
benefits. There is a lot of documentation, discussion, and reporting surrounding their implementations,
flowcharts, and recognition rates.
8
[10] Oualla, Mohamed & Sadiq, Abdelalim & Mbarki, Samir. (2015). COMPARATIVE STUDY
OF THE METHODS USING HAAR-LIKE FEATURES. INTERNATIONAL JOURNAL OF
ENGINEERING SCIENCES & RESEARCH TECHNOLOGY. 435. 35.

Three steps are involved in the detection process: gathering the object's defining characteristics,
processing the data, and building the detector in its final form. They will focus on the first phase.
Numerous methods have been employed, including texture, edge orientation, color information,
Haar-Like features, and more. Although a number of methods have been proposed for information
extraction that make use of the Haar-like characteristic, we are not aware of any surveys that
address this topic. Consequently, a comparative evaluation of several studies on Haar-Like
properties is presented in this work.

[11] H. J. Lee, I. Ullah, W. Wan, Y. Gao, Z. Fang, "Real-time vehicle make and model
recognition with the residual Squeeze Net architecture," Sensors, vol. 19, (5), pp. 982, 2019.

In this research, they examine a few-shot learning problem with a focus on vehicle make and model
detection in traffic surveillance images. Though they might be thought of as a more reliable option
than ALPR-based vehicle model recognition, image-based vehicle identification systems often
break down when an unseen vehicle enters the scene. Few-shot learning techniques might offer a
way around this unidentified class problem for car model recognition. In this study, we compare
two popular few-shot learning methods on a car model recognition task: weight imprinting and
closest class mean classifier. The proposed method seeks to preserve the high accuracy rate of the
base (existing) classes while achieving robust classification performance on new classes.

[12] Z. Dahirou, M. Zheng and M. Yuxin, "Face Detection with Viola Jones Algorithm," 2020
7th International Conference on Information Science and Control Engineering (ICISCE),
Changsha, China, 2020, pp. 602-606, doi: 10.1109/ICISCE50968.2020.00130.

The position and size of a humanoid face in digital photos can be controlled using a computer
technology called face detection; however, the recommended method concentrates on the image
itself rather than the location. Face detection, which combines AI, ML, and CV, is the initial step
in face recognition, according to P. Viola and M. J. Jones. The input image is initially transformed
to grayscale since working in a single image plane is significantly simpler and requires less data
processing than working with a three-dimensional colorful image without sacrificing important
information. For face identification, the Viola-Jones (VJ) Algorithm is employed. This process
yields more precise results and is faster than earlier approaches.

9
 CHAPTER 3
WORK DONE AND DETAILS

10
3.1 TOOLS USED
Hardware:

For the prototype gate:

Chop Saw, Drilling Machine, Drill Bits, Center Punch, Plier, Hammer, C Clamp, etc..

Software:

Raspbian OS, Raspberry Pi Imager, VNC Viewer, etc..

3.2 PROCESS FOLLOWED

To automate the sliding gate the main part is the controller, the controller is designed in such
a way that it is compatible with a sliding gate of any size and weight, and the gate will be
equipped with a rack and pinion mechanism according to the size of the gate and as per torque
requirement motor will be selected.

The process followed is :

1) Building of the Gate Model

Aluminum Square Pipes, Angles are used for constructing the frame. The Rolling wheels are
used for the frictionless sliding of the gate.

2) Installing Rack, Pinion, and Motor

The plastic Rack and Pinion are installed with a geared DC motor on the gate. This is the main
mechanism which drives the gate without human efforts.

3) Installing Sensor and Switches

To detect the status of the gate, Push button switches are fixed for the user input and also the
IR Sensor

11
Fig. 3.2.1 Block Diagram of The Controller

Fig. 3.2.2 Schematic Diagram

12
4) Face Detection System

The raspberry pi is interfaced with the pi camera module. Face detection system detect the
face and process it with the data set and commands the microcontroller

3.3 MATERIALS USED

Fig. 3.3.1 Aluminum Pipe And Angles

The Aluminum is a light weight material which is

selected for the Gate prototype. Aluminium Angle
is used for the rail of the Gate. Square Pipes are
used for the frame. The thickness of the Angle is
2 mm and width is 15mm. The square pipe thickness is 0.3mm and it is 30mmX15mm.

Fig. 3.3.2 Rack and Pinion Gear

The nylon Rack and pinion gear are used for building
the mechanical mechanism which will deploy the
sliding gate. It converts the circular motion from the
Motor to the Linear motion of the gate. The dimensions
of the rack are ½ X 12 inches and it is
super glued over the gate. The Pinion gear has 1 inch diameter and thickness of ¾
inches.

Fig. 3.3.3 DC Geared Motor

The Pinion Gear is connected to the motor which rides the

rack. Rack is Super Glued over the Gate. The gear ratio
of the Motor helps to reduce the speed of operation. The
gears help to increase the torque of the motor. The
operating voltage of the motor is 12VDC. The RPM of
the motor is 60.

13
Fig. 3.3.4 IR SENSOR

IR sensors work based on the principle that objects emit infrared

radiation as heat. These sensors detect this emitted infrared
radiation and convert it into an electrical signal, which can then
be processed. hese sensors detect changes in infrared radiation
caused by movement of objects in their field of view. They are
commonly used in motion detetion.
is responsible for Opening and Closing of the gate. Relay Itself requires Relay Driver
Circuit which has components like transistors, diodes and resistors.

Fig. 3.3.5 12V DC Adapter

The 12V DC Adapter is a switch mode power supply which

converts the 230VAC into a 12Volt 2Amp DC power source.
The Power Supply power Up the 12V Motor. The 12V are
also used for the rest of the electronics.

Fig. 3.3.6 Pushbutton Switches

The Pushbutton switches are used for the user’s input. The push
buttons are of NO (normally open) type and have a pullup
resistor to normally provide a HIGH signal. When the button is
pressed it provides a LOW output, which is read and processed
by the microcontroller.

Fig. 3.3.7 L298N Dual H Bridge DC/Stepper Motor Driver Controller Moodule:

The L298N IC is designed to control the speed and direction of DC

motors or stepper motors. It consists of two H-bridge circuits, allowing
it to control two motors independently. An H-bridge is an electronic
circuit that enables bidirectional control of a motor. The L298N contains
two H-bridge circuits, each capable of driving one motor. The L298N
typically operates with a wide input voltage range, commonly from 7V
to 35V. This flexibility makes it suitable for a variety of applications.

14
Fig. 3.3.8 Raspberry Pi and Pi Camera

The Raspberry Pi 3 Model B+ is a popular single-board computer developed by the Raspberry Pi

Foundation. Here's some information about the Raspberry Pi 3 Model B+:

Processor: The Raspberry Pi 3 Model B+ features a Broadcom

BCM2837B0 quad-core ARM Cortex-A53 processor running at
1.4 GHz. This processor provides improved performance
compared to previous models.

Memory: It is equipped with 1GB LPDDR2 SDRAM, providing

sufficient memory for various computing tasks and applications.

Connectivity:
Ethernet: Gigabit Ethernet (10/100/1000 Mbps) for wired network connectivity.
Wireless: Dual-band 2.4 GHz and 5 GHz IEEE 802.11.b/g/n/ac wireless LAN for Wi-Fi
connectivity.
Bluetooth: Bluetooth 4.2/BLE (Bluetooth Low Energy) for wireless communication with
Bluetooth-enabled devices.
Ports:

USB: Four USB 2.0 ports for connecting peripherals such as keyboards, mice, and external storage
devices.
HDMI: Full-size HDMI port for connecting to displays or TVs.
Audio/Video: Combined 3.5mm audio jack for audio output and composite video.
Camera Interface: CSI camera interface for connecting Raspberry Pi Camera modules.
Display Interface: DSI display interface for connecting Raspberry Pi Touchscreen displays.
GPIO: 40-pin GPIO (General Purpose Input/Output) header for interfacing with external devices
and circuits.

Operating System Compatibility: The Raspberry Pi 3 Model B+ supports a variety of operating

systems, including Raspberry Pi OS (formerly Raspbian), Ubuntu, and other Linux distributions. It
is also compatible with Windows 10 IoT Core.

Power: It can be powered using a micro USB power supply with a voltage rating of 5V and a
current rating of at least 2.5A.

Form Factor: The Raspberry Pi 3 Model B+ has the same form factor as its predecessor, the
Raspberry Pi 3 Model B, with dimensions of 85.6mm x 56.5mm x 17mm.

Usage: The Raspberry Pi 3 Model B+ is widely used for various projects and applications,
including home automation, media centers, retro gaming consoles, IoT (Internet of Things)
15
devices, educational projects, and prototyping

The Raspberry Pi Camera is a small, affordable, and versatile camera module designed specifically
for use with Raspberry Pi single-board computers. Here's some information about the Raspberry Pi
Camera:

Types:
Raspberry Pi Camera Module V1: The first version of the camera module features a fixed-focus
lens and a resolution of 5 megapixels (2592 × 1944 pixels). It connects to the Raspberry Pi via a
ribbon cable. Raspberry Pi Camera Module V2: The second version features improvements over
the V1 module, including better optics and a larger aperture. It retains the same 5-megapixel
resolution but offers improved image quality and low-light performance.
Raspberry Pi High-Quality Camera: This camera module features a larger 12.3-megapixel Sony
IMX477 sensor and supports interchangeable lenses. It offers higher resolution and improved
image quality compared to the previous camera modules.

Features:
Compact Size: The Raspberry Pi Camera modules are small and lightweight, making them ideal
for embedded projects and applications where space is limited.
Easy Connectivity: The camera modules connect directly to the Raspberry Pi's camera interface
via a ribbon cable, making it easy to integrate them into projects.
Versatility: The camera modules support various resolutions and frame rates, allowing users to
capture still images or video footage at different quality levels.
Software Support: The Raspberry Pi Camera modules are supported by the official Raspberry Pi
OS (formerly Raspbian) and third-party software libraries. Users can easily capture images or
record videos using Python scripts or command-line tools.
Interchangeable Lenses: The Raspberry Pi High-Quality Camera supports interchangeable lenses,
allowing users to customize the field of view and focal length for their specific application
requirements.

16
3.4 COSTING
Table 3.1: List of Components, their specifications and Estimated Costing

Sr Tentative Components Specifications Quantity Costing

No. (Approx.)

1) Raspberry Pi – 1 4000

2) Pi Camera – 1 400

3) Pi Case – 1 300

4) L298N Dual H bridge _ 1 350

Motor Driver
5) Motor -- 1 150

6) IR sensor _ 1 30

7) Adaptor 12v 1A 1 150

8) Push Button _ 1 30

18
 CHAPTER 4

RESULTS AND DISCUSSION

19
4.1 RESULT

Object Detection:

Our first objective was to accurately detect humans and number plates within the field
of view of the gate's camera. We utilized a pre-trained ML model which uses Haar
Cascade and OCR (Optical Character Recognition) to achieve this goal.

Object Recognition:

Once objects were detected, our next objective was to recognize them in real-time.
We utilized the for speeding up the face recognition process.

Finally, our goal was to utilize the object tracking information to control the sliding
gate.

In the proposed system, real time face detection and recognition is done where the
image is matched with the predefined database. If a match is foundthen it outputs
“True” which is interpreted by the microcontroller as to open the gate.
The license plate is detectedand the number is obtained in the form of a text input which
is further checked with the database and if a match is found, then the gate is opened.

Our results
demonstrate that
utilizing computer
vision and machine
learning techniques
can be an effective
way to control a sliding gate. The accuracy of object
detection and tracking was deemed sufficient for our
project's goals.

Overall, our project demonstrates the potential of utilizing these technologies for other
applications, such as security systems.

20
 Safety Feature

Face Capturing

21
License Plate detection:

Step 1: GrayScale Conversion

Step 2. Detected no. plate

Final detected output

22
 CHAPTER 5
SUMMARY AND CONCLUSION

23
5.1 SUMMARY

A sliding door mechanism with a facial recognition and license plate detection system is an
advanced security system that uses computer vision algorithms to recognize and authenticate
individuals as they enter a building or restricted area. The system's camera module captures live
video footage of people and cars as they get closer to the sliding door. Deep learning algorithms
are then used to analyze the video footage, enabling the system to accurately identify and recognize
license plates and people's faces.

The gadget is made to work in real time and provide precise results in challenging weather and
lighting conditions. The sliding door mechanism has sensors to identify people and cars, and
the technology that recognizes license plates and faces faces initiates the identification process
automatically. The system can be integrated with other security systems, such alarms and
access control systems, to increase the overall security of the building or restricted area.

All things considered, the sliding door mechanism's face recognition and license plate
detection system offers a dependable and efficient security management solution, enabling
quick and accurate identification of people and cars while preventing unauthorized entry.

5.2 CONCLUSION
As a group, we started working on the project. The system may be upgraded and improved
with a lot more research, ideas, resources, and financial planning. Adding number plate
detection is undoubtedly one of the future scope's objectives. In this manner, the owner of the
car never needs to get out of it to get access. The suggested method is adaptable and can be
utilized in a variety of settings, such as flats and housing societies, minimizing the need for
human interaction. In addition to security, the technology allows for scheduling flexibility
because it eliminates the need for someone to get up in order to activate gates at night.

● It can be implemented in various places like home, housing societies etc.

● The system can be installed in apartments to prevent unauthorized entries.
● This technique may be utilized to increase door security for strangers without the
requirement for security personnel or spending too much time.
Eventually, the convenience and security of building entrances may be greatly increased by
integrating a facial recognition and license plate detection system into a sliding door mechanism.
The system provides seamless and efficient access control and enhances security by identifying
unauthorized individuals or vehicles. The system makes use of cutting-edge technology like
artificial intelligence and machine learning to accurately and quickly identify people and cars.
Overall efficiency and safety are raised as a result. Sliding doors with this technology incorporated
could be utilized in parking garages, apartment buildings, and commercial buildings, among other
places. All things considered, this state-of-the-art technology is a good substitute for enhancing
building security and access management.

24
5.3 FUTURE SCOPE
To provide a more seamless and effective user experience, the sliding door
mechanism's face recognition and license plate detection technologies may be
enhanced in the future and integrated with other technologies.

One potential area of study is the use of artificial intelligence (AI) to improve the
speed and accuracy of license plate recognition and facial recognition systems. This
could mean training the system to identify a wider variety of facial features and
license plate designs in addition to adapting to shifting lighting and weather
conditions.

Furthermore, the system might be linked to a home automation platform, allowing

users to remotely manage the door and monitor entry using a smartphone app or other
device.

Lastly, doors and other access points besides sliding doors may be used to operate the
facial recognition and license plate detection system. Access points such as automated
gates, garage doors, and others that could use enhanced security and access control
features could be included.

25
REFERENCES:

[1] R. Chen, "Automatic License Plate Recognition via sliding-window darknet-

YOLO deep learning," Image Vision Computation, vol. 87, pp. 47 -56, 2019.

[2] K. Bhosale, J. Jadav, S. Kalyankar, R. Bhambare, "Number Plate Recognition

System for Toll Collection," International Journal of Emerging Technology and
Advanced Engineering, vol. 4, (4), pp. 729-732, 2014.

[3] S. S. Farfade, M. J. Saberian and L. Li, "Multi-view face detection using deep
convolutional neural networks," in Proceedings of the 5th ACM on International
Conference on Multimedia Retrieval, 2015, pp. 643-650.

[4] P. Viola and M. J. Jones, "Robust real-time face detection," International Journal
of Computer Vision, vol. 57, (2), pp. 137-154, 2004.

[5] Hteik Htar Lwin, Aung Soe Khaing, Hla Myo Tun, “Automatic Door Access
System Using Face Recognition”, INTERNATIONAL JOURNAL OF SCIENTIFIC
& TECHNOLOGY RESEARCH VOLUME 4, ISSUE 06, JUNE 2015 ISSN 2277-
8616.

[6] K. Vikram and S. Padmavathi, "Facial parts detection using Viola Jones
algorithm," 2017 4th International Conference on Advanced Computing and
Communication Systems (ICACCS), 2017, pp. 1-4,
doi:10.1109/ICACCS.2017.8014636.

[7] Neetu Saini, zukhwinder Kaur, Hari Singh, A Review: Face Detection Methods
and Algorithms, International Journal of Engineering Research & Technology
(IJERT), ISSN: 2278-0181, 2 (6), June – 2013.

[8] N. Dileep kumar and S. Shanthi, “Automatic Gate using Face Recognition
Technique using HAAR Cascade Algorithm”, International Journal of Engineering and
Advanced Technology (IJEAT), vol. 9, no. 3, pp. 1302–1305, Feb. 2020, Doi:
10.35940/ijeat.C5195.029320.

[9] R. Baran, T. Rusc and P. Fornalski, "A smart camera for the surveillance of
vehicles in intelligent transportation systems," Multimedia Tools Appl, vol. 75, (17),
pp. 10471-10493, 2016.

[10] Oualla, Mohamed & Sadiq, Abdelalim & Mbarki, Samir. (2015).
COMPARATIVE STUDY OF THE METHODS USING HAAR-LIKE FEATURES.
INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH
TECHNOLOGY. 435. 35.

[11] H. J. Lee, I. Ullah, W. Wan, Y. Gao, Z. Fang, "Real-time vehicle make and model
recognition with the residual Squeeze Net architecture," Sensors, vol. 19, (5),
pp. 982, 2019.

26
[12] Z. Dahirou, M. Zheng and M. Yuxin, "Face Detection with Viola Jones
Algorithm," 2020 7th International Conference on Information Science and Control
Engineering (ICISCE), Changsha, China, 2020, pp. 602-606, doi:
10.1109/ICISCE50968.2020.00130.

[13] W. -y. LU and M. YANG, "Face Detection Based on Viola-Jones Algorithm

Applying Composite Features," 2019 International Conference on Robots & Intelligent
System (ICRIS), Haikou, China, 2019, pp. 82-85, doi: 10.1109/ICRIS.2019.00029.

[14] O. Kainz, M. Nguyen, F. Jakab, R. Petija, M. Michalko and G. Alexandrova,

"Students’ Attendance Monitoring through the Face Recognition," 2019 17th
International Conference on Emerging eLearning Technologies and Applications
(ICETA), Starý Smokovec, Slovakia, 2019, pp. 342-347, doi:
10.1109/ICETA48886.2019.9040157.

[15] M. F. Hirzi, S. Efendi and R. W. Sembiring, "Literature Study of Face

Recognition using The Viola-Jones Algorithm," 2021 International Conference on
Artificial Intelligence and Mechatronics Systems (AIMS), Bandung, Indonesia, 2021,
pp. 1-6, doi: 10.1109/AIMS52415.2021.9466010.

27
SOCIETAL RELEVANCE:
Face recognition and licence plate detection technologies integrated with sliding
door mechanisms can have various societal implications, including:

1) Enhanced Security:

The facial recognition and licence plate detection technology may be used to
prevent unauthorised access to restricted places including businesses, hospitals,
and schools. This will assist to strengthen security and lessen the danger of theft
or vandalism at these locations.

2) Contactless entry:

Following the COVID-19 epidemic, contactless entrance has become mandatory.

The incorporation of these devices into sliding door mechanisms can assist
minimise physical touch, hence minimising viral propagation.

3) Traffic Management:

Number plate recognition systems may be used to track the number of cars
entering and exiting a facility, which can help with traffic management and
planning.

4) Time and Attendance Management:

The facial recognition technology may be used to record employees' attendance,

which can aid in tracking their work hours and calculating their compensation.

5) Crime Prevention:

The licence plate detection system may be used to identify and monitor cars
involved in criminal activity. This helps to prevent and identify crimes like
robbery and auto theft.

Ultimately, incorporating facial recognition and licence plate detection systems

into sliding door mechanisms may assist increase security, decrease interaction,
improve traffic management, track time and attendance, and prevent crimes.

28
CO-PO MAPPING TABLE:

29
 Yeshwantrao Chavan College of Engineering
Project Preliminary Investigation Report

Name of Department:
Electronics and Telecommunication Engineering

Name of Project Guide:

Prof. Y. S. Kale

Students Details:
Roll No. Name of Student Email ID Mobile No.

59 Kushank Gokhale Kushankgokhale1302@gmail.com 74987 12137

109 Kashmira Ghodkhande 20010590@ycce.in 73500 13465

201 Anadi Vyas Vyasanadi@gmail.com 80980 47474

76 Sushrut Pantaone SushrutPantaone2002@gmail.com 77757 90756

Title of the Project:

AUTOMATIC SLIDING GATE CONTROL SYSTEM USING MACHINE LEARNING
AND COMPUTER VISION

Area of Project Work:

Computer Vision and Machine Learning - Sliding Gate (Hardware)

33
Problem Statement:
Designing a face recognition and license plate detection system for a sliding door mechanism
that ensures secure access control in a commercial or residential setting.

Many buildings have sliding door mechanisms, and it is crucial to make sure that only people
with permission can enter. The main difficulty lies in creating a system that can instantly
identify license plates and recognize people with accuracy.

Facial hair, glasses, and hats are examples of physical differences in appearance that the face
recognition and license plate identification system must be able to handle, in addition to
varying lighting and angles. Additionally, it needs to be able to recognize phony license
plates and faces that may be used to enter uninvited.

Security is a major concern, and the system must be designed to prevent hacking or
unauthorized access to the system's data. The system must ensure that the data collected is
secure and protected from cyber attacks, as well as physical attacks.

To Strict access control procedures must be implemented in order to guarantee the security
of the system. Examples of these procedures include restricting access to authorised persons
and making sure that all attempts at access are recorded and closely monitored. In addition,
the system ought to be built to withstand physical attacks and be impervious to tampering.

Ensuring the protection and safety of people and property ultimately depends on the
development of a face recognition and license plate detection system for a sliding door
mechanism. In addition to being intuitive and simple to use, the system needs to be precise,
dependable, and secure.

34
Prior Art (Patent Search):
Patent Title of Patent Existing Solutions
Application No. (Abstract of Patent)
Computer vision and The present invention encompasses software
US9527115B2 machine learning that brings together computer vision and
software for grading machine learning algorithms that can
and sorting plants evaluate and sort plants into desired
categories. While one embodiment of the
present invention is directed toward
strawberry plants, the software engine
described is not specifically designed for
strawberry plants but can be used for many
different types of plants that require
sophisticated quality sorting. The present
invention is a sequence of software
operations that can be applied to various
crops (or other objects besides plants) in a
reusable fashion.

KR20160040037A The object The present invention relates to an object

authentication authentication device by short-range video
method and detection of a multi-structure and a method
apparatus by the thereof. The device comprises: a distance
short-range video sensor (712); a camera (711) for recognizing
detection of the face of a person who passes; a face
multiple structure processing unit (110); a fingerprint
recognizing sensor (713) for recognizing a
fingerprint of the person who passes; a
fingerprint processing unit (210); a speed
improving unit (211) for increasing a
matching speed; a fingerprint database (612);
a face database (611); a network connecting
unit (510) connectable to an external terminal
through a wired/wireless network; and a
control unit (610) for controlling a lock
device of a door to be opened and closed
through authentication. Therefore, the device
increases processing speed and accuracy
when an object is authenticated.

35
US10438053B2 Biometric An exemplary embodiment of the present
identification invention provides a method of verifying an
systems and identity of a person-to-be-identified using
methods biometric signature data. The method
includes creating a face sample database
based on biometric signature data from a
plurality of individuals, calculating a feature
database by extracting selected features of
entries in the sample database, calculating
positive samples by calculating a feature
absolute value distance for a same position of
any two different images from one person,
calculating negative samples by calculating a
feature absolute value distance for a same
position of different people, calculating a key
bin feature using a learning algorithm,
calculating a classifier from the key bin
feature for use in identifying and
authenticating an acquired face image of a
person-to-be-identified and identifying and
authenticating the person-to-be-identified
using the classifier and the acquired face
image of the person-to-be-identified.

TW202213237A Security real-time A security real-time monitoring system

monitoring system includes at least one management device, a
plurality of lenses, a plurality of access
control devices, a plurality of lock devices
and a server. The management device is used
to input event data including time range data,
work time-consuming data and personnel
data. The lens is used to provide a plurality of
image data. The access control device is used
to input identification data. The lock device
can provide lock status data. The server is
connected to the management device, the
lens, the access control device and the lock
device. The default event data is saved in the
server, the personnel access data can be
obtained by the lens and the access control
device. The server compares the personnel
access data with the default event data and
issues a warning message if they are not
inconsistent.

36
US10930151B2 Roadside parking A roadside parking management method
management includes: receiving a monitoring area image
method, device, captured by a camera; dividing the
and system based monitoring area image to obtain a plurality of
on multiple tracking detection areas in the monitoring
cameras area image; monitoring at least one of a
vehicle and a license plate in the monitoring
area image; and determining parking event
information according to a tracking detection
area where the at least one of the vehicle and
the licence plate is located. The method can
improve the management efficiency of
parking events.

Literature Review:
Title of Paper Details of Literature Identified for
Publication with Project
Date and Year
“Automatic License Plate Vol. 87, pp. 47-56, 2019 Image Vision Computation
Recognition via sliding-
window darknet-YOLO deep
learning”

“Number Plate Recognition Vol. 4, (4), pp. 729-732, International Journal of Emerging
System for Toll Collection” 2014 Technology and Advanced
Engineering

“Multi-view face detection 2015, pp. 643-650 5th ACM on International

using deep convolutional Conference on Multimedia
neural networks” Retrieval
“Robust real-time face Vol. 57, (2), pp. 137- International Journal of Computer
detection” 154, 2004 Vision

“Automatic Door Access VOLUME 4, ISSUE 06, INTERNATIONAL JOURNAL

System Using Face JUNE 2015 ISSN 2277- OF SCIENTIFIC &
Recognition” 8616 TECHNOLOGY RESEARCH

37
 Current Limitations:
A facial recognition and licence plate detection system in a sliding door mechanism
currently has various limitations:

(1) Accuracy:

Lighting conditions, distance from the camera, facial expression, and angle of the face can
all impact the accuracy of face recognition and licence plate identification. As a result, the
system may not always correctly identify persons or licence plates, thereby posing a security
risk.

(2) Concerns about privacy:

The use of face recognition technology creates privacy concerns since it entails the
collection and storage of biometric data. People may be concerned about their faces being
scanned and saved, particularly if they are unaware that this is occurring.

(3) False positives and negatives:

The system can generate false positives when it mistakenly detects a person or licence plate,
and false negatives when it fails to recognise a person or licence plate. These mistakes can
cause annoyance, delays, and security breaches.

(4) Limited functionality:

Only facial recognition and licence plate detection are currently supported by current
technology. It cannot distinguish between authorised and unauthorised people or vehicles,
nor can it provide extra security features like biometric authentication or motion detection.

38
 Proposed Solution:
The following components might be included in a suggested solution for a facial recognition
and licence plate detection system in a sliding door mechanism:

(1) Camera system:

The initial component of this approach is a camera system capable of capturing crisp photos
of faces and licence plates. The camera should be positioned such that it can see the sliding
door mechanism's entrance and exit.

(2) Face recognition software:

The second component of the system is facial recognition software, which can identify and
match the faces of people entering and departing the sliding door mechanism. Face
recognition software should be able to recognise faces even in low-light settings and from
various angles.

(3) Licence plate recognition software:

The third component of the solution is licence plate recognition software, which detects and
reads vehicle licence plates as they enter and depart the sliding door mechanism. Even if the
licence plate is dusty, broken, or partially concealed, our programme should be able to
recognize it.

(4) Control system:

The fourth component of the solution is a control system that manages the sliding door
mechanism's opening and shutting depending on the findings of the face and licence plate
recognition software. This system should be able to recognise authorised people and vehicles
and enable them to enter and depart the sliding door mechanism.

(5) Database: The solution's fifth component is a database that holds the authorised faces
and licence plate numbers. The facial and licence plate recognition software may utilise this
information to authenticate the identities of persons and vehicles entering and departing the
sliding door mechanism.

39
 Objectives and Scope of Work:

Objectives:

A facial recognition and licence plate detection system in a sliding door mechanism may have
the following goals:

(1) Identify authorised persons:

The facial recognition system should identify and recognise authorised individuals, allowing
them to use the sliding door mechanism.

(2) Deny unauthorized access:

The facial recognition system should be able to detect unauthorised persons and prevent them
from using the sliding door mechanism.

(3) Record entry and exit:

The licence plate detection system should detect and record vehicle entry and exit via the
sliding door mechanism.

(4) Ensure security:

The facial recognition and licence plate detection system should improve the sliding door
mechanism's security by allowing only authorised persons and vehicles access.

(5) Provide Safety:

The system should be built to recognise faces and licence plates swiftly and efficiently in
order to reduce wait times for authorised persons and vehicles.

(6) Integrate with existing systems:

Face recognition and licence plate detection systems should be able to interface with current
security systems, such as alarms and CCTV cameras.

(7) Maintain privacy:

The system should be built to safeguard people' privacy and personal information by adhering
to appropriate data protection standards.

(8) Provide accurate and reliable data:

To assist security and management decision-making, the system should offer precise and
trustworthy data on the entrance and leave of persons and vehicles.

Scope of Work:

• Face recognition and licence plate detection software is being developed.

• The software is integrated with the sliding door mechanism.
• System testing to guarantee compliance with requirements and standards.

• System user manuals and documentation are provided.

40
 Feasibility Assessment:

I. Expected Outcomes of the Project:

(1) (1) It is anticipated that a sliding door mechanism with a face recognition and license plate detection
system will produce a more straightforward and safe access control system for a building or facility.
(2) (2) Using face recognition technology, the system would be able to identify authorized individuals and
allow them entry into the building without the need for physical keys or access cards. By preventing
unauthorized individuals from entering, this would increase security and streamline access for
authorized individuals to the building.
(3) Similarly, using licence plate recognition technology, the system could automatically identify
and authorise cars permitted entrance to the premises. This might be particularly beneficial for
parking garages or gated facilities, allowing for smooth entry and departure without the need for
drivers to roll down their windows or scan access cards.
(4) Overall, including facial recognition and licence plate detection technology into a sliding door
mechanism would result in a more efficient and secure access control system that would allow
authorised personnel and vehicles to enter and depart more quickly.

II. Innovation Potential:

(1) Enhanced security:

Using facial recognition and license plate detection technologies in sliding door systems could
significantly increase building security. This would make it possible to identify authorized
employees while preventing unauthorized individuals from entering the property.

(2) Improved access control:

Authorized workers may have automatic and seamless access to the facility by connecting the
facial recognition and license plate detection system to an access control system. By doing this,
the need for cumbersome and easily compromised manual entry methods like key cards and
passwords would be eliminated.

(3) Enhanced surveillance:

Sophisticated surveillance features including real-time tracking and monitoring of people coming
into and going out of the building may also be included in the system. This could help identify
potential security threats and give security personnel important information to review.

(4) Improved efficiency:

The facial recognition and license plate detection system has the ability to significantly increase building
access efficiency by automating the entering process. Employee wait times would be reduced, and overall
productivity would increase.

(5) Customization:
The system may be customized to meet the specific needs of any building, enabling features like
automated visitor check-ins and automated lockdown procedures in the event of a security
breach.Sliding door systems with facial recognition and license plate detection built in have the
potential to revolutionize building security and access control. This invention has the potential to
become a vital part of contemporary building management because it can boost efficiency and security
while providing insightful data for research.

41
III. Tasks Involved:

Some of the jobs involved in a facial recognition and licence plate detection system in a sliding
door mechanism are as follows:

(1) Image acquisition:

The system must be able to take photographs of both faces and licence plates. Installing cameras
or other imaging equipment in key locations to capture clear pictures is required.

(2) Image preprocessing:

Images must be treated to eliminate noise and distortion and improve their quality. This process
may include image scaling, cropping, and altering brightness and contrast.

(3) Face detection:

Using face detection methods such as Haar cascades or deep learning models, the system must
recognise faces in collected photos. The technology will be able to isolate the face from the
surroundings and focus on the facial characteristics as a result.

(4) Face recognition:

After detecting a face, the system must compare facial traits to a pre-existing database of faces
to decide if the individual is authorised to enter.

(5) Licence plate detection:

Using licence plate identification methods, the system must detect licence plates in collected
pictures. The technology will be able to separate the licence plate from the backdrop and focus
on the characters as a result.

(6) Licence plate recognition:

Once a licence plate has been spotted, the system must recognise the characters on the plate
using optical character recognition (OCR) methods. This allows the system to identify whether
or not the vehicle is authorised to enter.

(7) Decision making:

Based on the findings of facial recognition and licence plate recognition, the system must decide
whether or not to open the sliding door. If the individual and vehicle are authorised, the system
will open the entrance; otherwise, the door will remain closed.

(8) System integration:

Finally, the system must be coupled with the sliding door mechanism so that it may regulate
the door's opening and shutting depending on the findings of the face and licence plate
recognition. Installing extra hardware or software to permit communication between the
identification system and the door mechanism may be required.

42
IV. Expertise Required:

The following skills are necessary to create a facial recognition and licence plate detection system
in a sliding door mechanism:

(1) Computer Vision:

Computer vision expertise is required to design algorithms for facial recognition and licence
plate identification. The system should be capable of detecting and recognising faces and licence
plates in real time and with high accuracy.

(2) Machine Learning:

Understanding of machine learning is required for the development of models for facial
recognition and licence plate identification. To achieve high accuracy, the models should be
trained on a big dataset.

(3) Image Processing:

To preprocess the pictures acquired by the system's camera, image processing abilities are
required. Noise reduction, contrast enhancement, and picture normalisation are all techniques
that can assist increase the accuracy of face recognition and licence plate detection.

(4) Software Development:

Knowledge of software development is required to create the software that operates the system.
Writing code for picture capture, processing, and recognition is part of this, as is connecting the
system with the sliding door mechanism.

(5) Hardware Integration:

Knowledge of hardware integration is required to interface the software with the sliding door
mechanism. This includes choosing the right cameras and sensors, creating the cabling and
connections, and ensuring that the system's hardware and software perform in tandem.

(6) Security:
A thorough grasp of security is required to guarantee that the facial recognition and licence plate
detection system is safe and secure from hackers and unauthorised access.

(7) User Interface Design:

Because the system should be simple to use and engage with, user interface design skills are
essential to produce an intuitive and user-friendly interface.

(8) Testing and Evaluation:

Thorough testing and evaluation should be performed on the system to guarantee that it functions
accurately and reliably under all situations. Testing and evaluation expertise is thus required to
build appropriate test scenarios and assess the system's performance against preset criteria.

43
 V. Facilities Required:

The following facilities may be required to integrate a facial recognition and licence plate detection
system into a sliding door mechanism:

(1) Camera:

High-quality cameras are required to capture good photos of faces and licence plates. To achieve
reliable identification, the camera should have a high resolution and strong low-light capability.

(2) Image processing software:

To analyse the images taken by the camera and extract the data required for facial recognition and
licence plate detection, specialised image processing software is required.

(3) Database:

A database is needed to hold the images and data gathered by the camera for comparison and
identification. The database should be capable of handling massive volumes of data and have
effective search engines.

(4) Connectivity:

To enable remote monitoring and control, the system should be linked to a network, such as the
internet or a local area network.

(5) Power supply:

The sliding door mechanism should be powered by a dependable power source capable of handling
the increased demand imposed by the facial recognition and licence plate detection systems.

(6) Security features:

Because this is a security system, it is critical that it has strong security measures in place to prevent
unauthorised access and data breaches.

(7) Integration with the sliding door mechanism:

The system should be built to function in sync with the motions of the sliding door mechanism.

(8) User interface:

To engage with the system and access its capabilities, such as monitoring and operating the door
and reviewing recorded data, users require an intuitive and user-friendly interface.

44
 Milestones and Time Plan:
Task J A S O N D J F M A
U U E C O E A E A P
L G P T V C N B R R

2022 2022 2022 2022 2022 2022 2023 2023 2023 2023

Desig Conceptual ✔
n Design

Detailed ✔
design

Design ✔
Modification

Final Design ✔

Devel Procurement ✔ ✔
op (If any)

Prototyping ✔ ✔

Modification ✔

Deliv Testing and ✔

er Validation

Final ✔ ✔
Modification

IPR / patent ✔ ✔
draft

Thesis and ✔ ✔
Poster

Signature of Project Guide Signature of HOD

45