Docsity
Log inSign up
Docsity
Prepare for your exams
Prepare for your exams

Study with the several resources on Docsity

Earn points to download
Earn points to download

Earn points by helping other students or get them with a premium plan

Guidelines and tips
Guidelines and tips
Sell on Docsity
Sell on Docsity
Log inSign up

Prepare for your exams

Study with the several resources on Docsity

Find documents

Prepare for your exams with the study notes shared by other students like you on Docsity

Search Store documents

The best documents sold by students who completed their studies

Search through all study resources
Docsity AINEW

Summarize your documents, ask them questions, convert them into quizzes and concept maps

Explore questions

Clear up your doubts by reading the answers to questions asked by your fellow students

Earn points to download

Earn points by helping other students or get them with a premium plan

Share documents
download point icon20 Points

For each uploaded document

Answer questions
download point icon5 Points

For each given answer (max 1 per day)

All the ways to get free points
Get points immediately

Choose a premium plan with all the points you need

Study Opportunities

Choose your next study program

Get in touch with the best universities in the world. Search through thousands of universities and official partners

Community

Ask the community

Ask the community for help and clear up your study doubts

University Rankings

Discover the best universities in your country according to Docsity users

Free resources

Our save-the-student-ebooks!

Download our free guides on studying techniques, anxiety management strategies, and thesis advice from Docsity tutors

From our blog

Exams and Study
Go to the blog

door locking system with facial recognition with ai integration, Thesis of Internet and Information Access

SRM Institute Of Science & TechnologyInternet and Information Access

a internet of things project report on door locking system with facial recognition with ai integration

Typology: Thesis

2024/2025

Available from 06/13/2025

anshy-prabha
anshy-prabha 🇮🇳

5 documents

1 / 7

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
1
IoT (Internet of Things)Based Door Locking System
with Facial Recognition with AI Integration
Govind Mahadev, Sinan Kabeer, Md Nadhir
RA2311003050269 RA2311003050285 RA2311003050218
Department of Computer Science and Engineering,
SRM University
Abstract-
This paper is a presentation that aims
to give a deeper understanding of an
IoT-based door-locking system that
uses facial detection and recognition
for enhanced security and automation.
In this era, with the advancements
happening in the field of the Internet
of Things (IoT) and artificial
intelligence (AI), traditional security
mechanisms are evolving toward
smarter and more reliable solutions.
The proposed system employs a camera
module for real-time face detection and
recognition, a microcontroller (Arduino
with ESP32), and a solenoidal door lock
mechanism. The system ensures access
control by comparing detected facial
features with stored biometric data.
This paper discusses the architecture,
implementation, working principle, and
security considerations of the proposed
system.
Keywords:- Internet of Things,
Artificial intelligence, Biometric
Authentication, Smart lock, Facial
Recognition.
I.INTRODUCTION
Conventional security systems, such as
key-based locks and password-protected
entry mechanisms, have significant.
limitations, including the risk of key
misplacement, password breaches, and
unauthorized duplication. In the coming
future, security and access control play a
vital role in modern residential,
commercial, and Industrial
infrastructures. The adoption of biometric
authentication methods, such as facial
recognition, offers a more secure and
user-friendly approach to access control.
Facial recognition technology leverages
artificial intelligence and machine
learning algorithms to identify and
authenticate individuals based on their
unique facial features. Integrating this
technology with an IoT-enabled smart
locking system enables access control and
real-time authentication. In this paper, we
provide a working model of an IoT-based
door lock that can be implemented in
small-scale houses.
pf3
pf4
pf5

Partial preview of the text

Download door locking system with facial recognition with ai integration and more Thesis Internet and Information Access in PDF only on Docsity!

IoT (Internet of Things)Based Door Locking System

with Facial Recognition with AI Integration

Govind Mahadev, Sinan Kabeer, Md Nadhir RA2311003050269 RA2311003050285 RA Department of Computer Science and Engineering, SRM University Abstract- This paper is a presentation that aims to give a deeper understanding of an IoT-based door-locking system that uses facial detection and recognition for enhanced security and automation. In this era, with the advancements happening in the field of the Internet of Things (IoT) and artificial intelligence (AI), traditional security mechanisms are evolving toward smarter and more reliable solutions. The proposed system employs a camera module for real-time face detection and recognition, a microcontroller (Arduino with ESP32), and a solenoidal door lock mechanism. The system ensures access control by comparing detected facial features with stored biometric data. This paper discusses the architecture, implementation, working principle, and security considerations of the proposed system. Keywords:- Internet of Things, Artificial intelligence, Biometric Authentication, Smart lock, Facial Recognition. I.INTRODUCTION Conventional security systems, such as key-based locks and password-protected entry mechanisms, have significant. limitations, including the risk of key misplacement, password breaches, and unauthorized duplication. In the coming future, security and access control play a vital role in modern residential, commercial, and Industrial infrastructures. The adoption of biometric authentication methods, such as facial recognition, offers a more secure and user-friendly approach to access control. Facial recognition technology leverages artificial intelligence and machine learning algorithms to identify and authenticate individuals based on their unique facial features. Integrating this technology with an IoT-enabled smart locking system enables access control and real-time authentication. In this paper, we provide a working model of an IoT-based door lock that can be implemented in small-scale houses.

II.LITERATURE REVIEW

There have been numerous studies that went into the field of facial recognition and biometric authentication techniques. These researches started as early as 1964 when Woodrow Bledsoe, Helen Chan Wolf, and Charles Bisson created their first automated facial recognition. Then came Takeo Kanade who came up with an idea for a face-matching system which could calculate the distance between facial features. These researchers paved the way for the early 2000s machine learning algorithms which could detect faces with even greater accuracy. From this IoT based facial recognition has come a long way but there are still some hurdles left, microcontrollers such as Raspberry Pi and ESP32 facilitate remote access, automation, and cloud-based logging but face challenges like computational complexity, privacy concerns, and environmental factors which affects the accuracy of facial recognition. This paper tries to fix some of these problems by combining different research in this field. III.SYSTEM ARCHITECTURE III.I Components The system module consists of:  Camera Module: The OV camera is used to capture the images of individuals trying to access the door.  Microcontroller: An ESP microcontroller is used to process the images taken by the camera and uses these images to process facial recognition and control the locking mechanism.  Facial Recognition Module: We use deep learning AI-based learning modules like OpenCV and TensorFlow for real-time facial recognition and detection.  Electronic Locking Mechanism: System access control is done with the help of a solenoidal lock.  IoT Cloud Platform: A cloud- based platform like Firebase is used for the storage and processing of access logs and mobile notifications.  Mobile/Web Application: Remote monitoring, user management, and real-time notifications are enabled by this. III.II System Workflow Algorithm

  1. The camera is used to capture the images of any individual that’s attempting to access the door.
  2. The captured image is run through the facial recognition module which processes the image and compares the image with the stored biometric data.
  3. If the image passes the authentication with success, the microcontroller sends a signal which will then unlock the lock.
  4. If the image fails the authentication, an alert message is sent to the user's phone and the access is denied. There will also be an alarm sound to alert nearby people.
  5. Every access attempt, whether successful or unsuccessful, is logged and stored in a secure cloud database for further monitoring. IV.IMPLEMENTAION AND METHODOLOGY IV.I Hardware Implementation  Processing unit: ESP32 CAM is used for computation and communication.  Camera Module: The OV camera is used to capture the facial image.  Locking Mechanism: A solenoid lock

V.SECURITY CONSIDERATION

To ensure the security and reliability of the system we have included certain measures:  Data Encryption: Biometric data and communication between devices are encrypted using ASE- 265 or RSA encryption.  Spoof Detection: Anti-spoofing techniques, such as liveness detection through blink or movement analysis, prevent unauthorized access using images or videos.  Access Logs: Every access attempt is recorded in a secure database for additional security monitoring and recording.  Power-Backup: There will be a power backup provided to the device in case of emergency power failure. It is also needed as a flashlight is provided inside the device as it is more accurate with sufficient light.  Alarm and 100-Text: There will be a separate database of images with certain images that we would have added from police or criminal records of individuals with theft backgrounds. If the camera picks up these individuals an alarm is sounded from the device and an emergency text is sent to the nearby police station. VI.RESULTS AND DISCUSSION The prototype was tested in various environmental conditions to evaluate its performance in terms of accuracy, response time, and security. The system demonstrated high accuracy in facial recognition under well-lit conditions but in low-light conditions, the accuracy was low and can be cited as a limitation. This is solved by the flashlight and infrared assist provided. The IoT integration has enabled real-time alerts and remote access, making this system a necessity in smart homes and other places as a security system. The system and devices provide a better way of home security but there are still potential challenges such as privacy concerns which require further investigation. VII.CONCLUSION AND FUTURE WORK This study presents a smart, IoT-enabled door-locking system that integrates facial recognition for secure access control. Future research will focus on improving recognition accuracy in challenging environments, implementing edge computing for faster processing, and integrating multi-modal authentication methods, such as fingerprint recognition and voice verification. The proposed system eliminates the need for physical keys or passwords, offering a seamless and secure authentication mechanism. The integration of cloud-based IoT platforms ensures remote monitoring, logging, and real-time notifications, enhancing overall security and convenience. REFERENCE Amanullah, M. (2013).Microcontroller Based Reprogrammable Digital Door Lock Security System using Keypad &GSM/CDMA Technology, IOSR Journal of Electrical and Electronics Engineering, 4(6):38-42. Zhao, W., Chellappa, R., Phillips, P.J. and Rosenfeld, A. (2003). Face Recognition: A Literature Survey, Center for Automation Research, University of Maryland College, USA. Gordon, G. G. (1991). Face recognition based on depth maps and surface curvature, Proc. SPIE 1570, Geometric Methods in Computer Vision, (1, September 1991);

https://doi.org/10.1117/12. 8 Schneirdeman, H. A. and Kanade, T. (1998). Probabilistic modelling of local Appearance and spatial reationships for object recognition,Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kirby, M., and Sirovich, L. (1990). Application of the Karhunen- Loeve Procedure for the Characterization of Human Faces. IEEE Trans. Pattern Anal. Mach. Intell., 12:103-108. Belhumeur, P.N., Hespanha, J.P., and Kriegman, D.J. (1997). Eigenfaces vs. Fisher faces: Recognition Using Class Specific Linear Projection. IEEE Trans. Pattern Anal. Mach. Intell., 19:711-720. Etemad, K., and Chellappa, R. (1997). Discriminant Analysis for Recognition of Human Face Images (Invited Paper). AVBPA. GU, L., Li, S. Z., andZhang, H. J. (2001). Learning probabilistic distribution model for multiview face dectection, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 Wiskott, L. Fellous, J.L. Krüger, N. and Malsburg, C., (1997). IEEE Transactions on Pattern Analysis and Intelligence, 19(7):775- Cox, I.J., Ghosn, J., and Yianilos, P.N., (1996). Feature-based facerecognition using mixture-distance. Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 209-216. Roy, S., Uddin, M.N., Haque, M.Z. and Kabir, M.J.(2018). Design and Implementation of the Smart Door Lock System with Face Recognition Method using the Linux Platform Raspberry Pi, International Journal of Computer Science and Network, 7(6): 382-388.