SlideShare ist ein Scribd-Unternehmen logo
1 von 15
Facial Recognition Door Unlock
Submitted in the partial fulfilment
for the award of the degree of
BACHELOROF ENGINEERING
IN
Computer Science and Engineering
with Specialization in
Artificial Intelligence and Machine Learning
Submitted by:
Sagar Vashist 21BCS6597
Yuboraj Ganguly 21BCS6602
Sameesh Bagga 21BCS6623
Under the Supervision of:
Mrs. Rajat Tiwari
With the rise of smart home technology, many are looking for ways
to increase the security and convenience of their homes & property.
One potential solution is a facial recognition door unlock system,
which uses advanced technology to grant access to authorized users.
Facial recognition technology has become increasingly sophisticated
in recent years, thanks to advances in artificial intelligence and
machine learning. These systems can now accurately recognize
individuals based on facial features, even in challenging lighting
conditions or from unusual angles.
In addition to providing a high level of security, a facial recognition
door unlock system can also be very convenient for users. They don't
need to remember a code or carry a key; instead, they can simply
approach the door and be granted access automatically.
Introduction
This project aims to explore the potential of facial recognition
technology for home security, by building a prototype facial
recognition door unlock system. We will use a combination of
hardware and software tools to create a system that can accurately
recognize authorized users and grant them access to a locked door.
While facial recognition technology has many potential benefits, it's
also important to consider the potential risks and challenges. We will
take a comprehensive approach to security and privacy, using
advanced encryption and ensuring that user data is protected at all
times.
Ultimately, the goal of this project is to create a secure and
convenient facial recognition door unlock system that can be used in
real-world applications. By demonstrating the potential of this
technology, we hope to inspire further innovation in the field of
smart home security.
Problem
Formulation
1. Security: One of the primary reasons for implementing facial recognition
technology is to enhance security measures. Facial recognition can be a highly secure
way to authenticate and grant access to a restricted area or building.
2. Convenience: Facial recognition can offer a convenient alternative to traditional
key or card-based entry systems. Users can simply walk up to the door and be
granted access without the need for any physical keys or access cards.
3. Accuracy: Facial recognition technology has become highly accurate in recent
years, making it a reliable means of authentication. This can help prevent
unauthorized access and improve security.
5. Cost-effectiveness: Facial recognition technology can be a cost-effective solution
in the long run, as it eliminates the need for physical keys and access cards.
Additionally, it can reduce the need for security personnel to monitor access points.
6.User-friendly: Facial recognition technology is user-friendly, as users don't need to
carry anything extra to gain access. This can improve the overall user experience and
reduce frustration associated with lost or forgotten access cards.
Overall, a facial recognition door unlock project can offer a highly secure,
convenient, and cost-effective solution for access control, making it a compelling
option for a wide range of settings.
Objectivesof the Work
02
Ensure that the system is secure
and cannot be easily bypassed
by unauthorized users, through
measures such as encryption,
user authentication, and anti-
spoofing techniques.
03
Test the system thoroughly to
ensure that it works reliably in
a range of lighting conditions,
with different camera angles
and distances, and with a
variety of facial features and
expressionsud technology.
01
Develop a facial recognition
system that can accurately
identify authorized individuals
and grant them access to a
locked door.
04
Evaluate the system's accuracy and
speed of recognition, and optimize its
performance through machine learning
and other techniques.
05
Document the project thoroughly, including its
design, implementation, testing, and evaluation, so
that others can replicate or build upon the work in
the future.
Methodology used
The methodologies in this project will include hardware and
software development and integration of both. The
hardware development will involve selecting and integrating
a low-cost camera, microcontroller, and locking
mechanism. In this algorithm will take a few images from
different angles and then check if the user is registered. The
software development will involve developing facial
recognition algorithms, image processing, and database
management. The integration will involve testing and
optimizing our system for accuracy, speed, and reliability
The training of a face-unlocking CNN involves
feeding it thousands of images of faces from a
variety of angles, lighting conditions, and
expressions. One such system is the Face Net
system developed by Google, which uses a deep
convolutional neural network (CNN) to extract
facial features and then applies a distance metric to
determine the similarity between two faces.
Another system is the Deep Face system developed
by Facebook, which uses a deep neural network to
extract facial features and then applies a SoftMax
classifier to classify the faces. Therefore, there is a
need for an alternative algorithm that can provide
high accuracy with low computational costs.
Use of CNN
Convolutional layer:
Activation layer: Pooling layer:
Fully Connected
Layers:
Batch Normalization
layer:
CNN L
CN
ayers
According to the evaluation, the facial recognition system
achieved an overall
accuracy of 95%. This indicates that the system was able to
recognize the
person correctly in most cases.
The FAR was found to be 2%, indicating low susceptibility to
fraudsters. The
FRR is 3%, indicating that the system correctly identified the
matching faces
with high accuracy.
Determines whether it is an authorized person or not based on
the pre-registered
for pre-stored images in the database
Results
Basedon the results of the tests that havebeen carried out, it can
be concluded that the system runs as expected and can be used
as a facial recognition-based automatic door lock system. When
the facial image cannot be recognized or is unsuccessful in being
identified, the door will remain closed. Therefore, the system can
beinstalled asasecurityfeature on adoor to aprivate room.
The latest development of 3D sensors points to a new approach
to facial recognition that may be able to get through the primary
obstacles, such as changes in physical appearance, the ageing
process, position, changes in light intensity, and more generally,
facial emotions, missing data, cosmetics, and occlusions. In the
event of problematic acquisition settings, the geometry
information offered by facial datasets could greatly increase the
accuracy of facial identification.
Results
Based on the results of the tests that have been carried
out, it can be concluded that the system runs as expected
and can be used as a facial recognition-based automatic
door lock system. When the facial image cannot be
recognized or is unsuccessful in being identified, the door
will remain closed. Therefore, the system can be installed
as a security feature on a door to a private room.
The latest development of 3D sensors points to a new
approach to facial recognition that may be able to get
through the primary obstacles, such as changes in
physical appearance, the ageing process, position,
changes in light intensity, and more generally, facial
emotions, missing data, cosmetics, and occlusions. In the
event of problematic acquisition settings, the geometry
information offered by facial datasets could greatly
increase the accuracy of facial identification.
Conclusion
Highlights
1. Facial recognition technology can
provide a convenient and secure
way to unlock doors, eliminating
the need for keys or access codes.
2. Using a camera to capture an
image of the user's face, the
software can compare it to a
database of authorized users to
determine if access should be
granted.
3. This technology can be especially
useful in high-security
environments such as government
buildings, research facilities, or
financial institutions.
4. By integrating facial recognition
with other security systems such as
alarms and cameras, the door
unlock project can provide a
comprehensive security solution
Conclusion
Pitfalls
Facial recognition technology has come under criticism
for potential biases, inaccuracies, and privacy
concerns. It is essential to consider these issues when
implementing the technology and ensure that the
system is fair and transparent.
The accuracy of facial recognition technology can be
affected by various factors such as lighting, angles,
and facial expressions. The system may fail to
recognize authorized users, resulting in frustration and
inconvenience.
It is crucial to implement proper security protocols to
prevent unauthorized access to the facial recognition
system itself, as this can compromise the entire
security system.
Finally, the cost of implementing a facial recognition
door unlock project can be significant, requiring
hardware, software, and ongoing maintenance
expenses. A cost-benefit analysis should be conducted
to ensure that the benefits of the project justify the
investment.
Improved accuracy: As facial recognition technology continues to advance,
there will likely be further improvements in accuracy, particularly in challenging
lighting conditions or with subjects wearing masks or other face coverings.
Scalability: Currently, most facial recognition systems are designed to work with
a relatively small number of users. In the future, it may be possible to scale up
the system to work with larger groups of people, potentially making it useful for
access control in public spaces.
Multi-factor authentication: While facial recognition can be an effective way to
authenticate users, it may be even more secure to combine it with other forms
of authentication, such as passwords or biometric data from other parts of the
body (such as fingerprints or iris scans).
Privacy concerns: Facial recognition technology has come under scrutiny due to
concerns about privacy and potential misuse. Future developments in this area
may focus on ways to mitigate these concerns, such as incorporating encryption
or anonymization techniques.
Future
Scope
References
[1]. O. Deniz, M. Castrillon, M. Hernandez, “Face recognition using independent component analysis and support vector machines,” Pattern Recognition
Letters, vol. 24, pp. 2153-2157, 2003.
[2]. I.J. Cox, J. Ghosn, and P.N. Yianios, “Feature-Based face recognition using mixture-distance,” Computer Vision and Pattern Recognition, 1996.
[3]. M. Turk and A. Pentland, “Eigenfaces for recognition,” J. Cognitive Neuroscience, vol. 3, pp. 71-86, 1991.
[4]. Ho-Man Tang, Michael Lyu, and Irwin King, "Face recognition committee machine," In Proceedings of IEEE International Conference on Acoustics,
Speech, and Signal Processing (ICASSP 2003), pp. 837-
840, April 6-10, 2003
[5]. "Design and Implementation of a Facial Recognition Door Lock System" by D. D. Yang, D. Y. Lee, and J. H. Kim -Link: https://www.mdpi.com/1424-
8220/19/13/3009
[6]."Smart Door Lock using Facial Recognition System" by S. Senthil Kumar, S. Sathish Kumar, and S. Sivakumar.
(https://ieeexplore.ieee.org/document/9041969)
[7]. "Facial Recognition Door Lock Security System using IoT" by M. B. Khan, M. A. Al-Garadi, and A. R. Khan. (https://www.mdpi.com/2504-
3900/25/1/29)
[8]. "Facial Recognition-Based Door Lock System Using Deep Learning" by H. M. Elhoseny, M. A. M. Mahmoud, and S. M.
Riad. (https://www.mdpi.com/1424-8220/20/23/6765)

Weitere ähnliche Inhalte

Ähnlich wie Facial Recognition Door unlock using Machine Learning.

Face Recognition Home Security System(Slide)
Face Recognition Home Security System(Slide)Face Recognition Home Security System(Slide)
Face Recognition Home Security System(Slide)Suman Mia
 
Attendance System using Face Recognition
Attendance System using Face RecognitionAttendance System using Face Recognition
Attendance System using Face RecognitionIRJET Journal
 
Face recognition technology - BEST PPT
Face recognition technology - BEST PPTFace recognition technology - BEST PPT
Face recognition technology - BEST PPTSiddharth Modi
 
IRJET - Face Detection and Recognition System
IRJET -  	  Face Detection and Recognition SystemIRJET -  	  Face Detection and Recognition System
IRJET - Face Detection and Recognition SystemIRJET Journal
 
RAT Trap: Home Surveillance System Using IoT & AI
RAT Trap: Home Surveillance System Using IoT & AIRAT Trap: Home Surveillance System Using IoT & AI
RAT Trap: Home Surveillance System Using IoT & AIIRJET Journal
 
Facial Recognition System For Access Control
Facial Recognition System For Access ControlFacial Recognition System For Access Control
Facial Recognition System For Access ControlMd. Saddam Hossain Noyon
 
Development of Real Time Face Recognition System using OpenCV
Development of Real Time Face Recognition System using OpenCVDevelopment of Real Time Face Recognition System using OpenCV
Development of Real Time Face Recognition System using OpenCVIRJET Journal
 
Face recognition
Face recognition Face recognition
Face recognition Chandan A V
 
IRJET - Face Recognition Door Lock using IoT
IRJET - Face Recognition Door Lock using IoTIRJET - Face Recognition Door Lock using IoT
IRJET - Face Recognition Door Lock using IoTIRJET Journal
 
Final PPT.pptx
Final PPT.pptxFinal PPT.pptx
Final PPT.pptxGAMINGRBF
 
Development of anti theft security system
Development of anti theft security systemDevelopment of anti theft security system
Development of anti theft security system96452128
 
Face Recognition System using OpenCV
Face Recognition System using OpenCVFace Recognition System using OpenCV
Face Recognition System using OpenCVIRJET Journal
 
Gated Communities Access Control Solution
Gated Communities Access Control SolutionGated Communities Access Control Solution
Gated Communities Access Control Solutionphilipthomas428223
 
Facial Recognition Mini project 3.pdf
Facial Recognition Mini project 3.pdfFacial Recognition Mini project 3.pdf
Facial Recognition Mini project 3.pdftalkaton
 
Face Recognition Based Automated Student Attendance System
Face Recognition Based Automated Student Attendance SystemFace Recognition Based Automated Student Attendance System
Face Recognition Based Automated Student Attendance Systemijtsrd
 
Attendance management system using face recognition
Attendance management system using face recognitionAttendance management system using face recognition
Attendance management system using face recognitionIAESIJAI
 
IRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric LearningIRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric LearningIRJET Journal
 
IRJET - Smart Doorbell System
 IRJET - Smart Doorbell System IRJET - Smart Doorbell System
IRJET - Smart Doorbell SystemIRJET Journal
 

Ähnlich wie Facial Recognition Door unlock using Machine Learning. (20)

Face Recognition Home Security System(Slide)
Face Recognition Home Security System(Slide)Face Recognition Home Security System(Slide)
Face Recognition Home Security System(Slide)
 
Attendance System using Face Recognition
Attendance System using Face RecognitionAttendance System using Face Recognition
Attendance System using Face Recognition
 
Face recognition technology - BEST PPT
Face recognition technology - BEST PPTFace recognition technology - BEST PPT
Face recognition technology - BEST PPT
 
IoT based facial recognition door access control home security system using r...
IoT based facial recognition door access control home security system using r...IoT based facial recognition door access control home security system using r...
IoT based facial recognition door access control home security system using r...
 
IRJET - Face Detection and Recognition System
IRJET -  	  Face Detection and Recognition SystemIRJET -  	  Face Detection and Recognition System
IRJET - Face Detection and Recognition System
 
RAT Trap: Home Surveillance System Using IoT & AI
RAT Trap: Home Surveillance System Using IoT & AIRAT Trap: Home Surveillance System Using IoT & AI
RAT Trap: Home Surveillance System Using IoT & AI
 
Facial Recognition System For Access Control
Facial Recognition System For Access ControlFacial Recognition System For Access Control
Facial Recognition System For Access Control
 
Development of Real Time Face Recognition System using OpenCV
Development of Real Time Face Recognition System using OpenCVDevelopment of Real Time Face Recognition System using OpenCV
Development of Real Time Face Recognition System using OpenCV
 
Implementation of Biometric Based Electoral Fraud Desisting System
Implementation of Biometric Based Electoral Fraud Desisting SystemImplementation of Biometric Based Electoral Fraud Desisting System
Implementation of Biometric Based Electoral Fraud Desisting System
 
Face recognition
Face recognition Face recognition
Face recognition
 
IRJET - Face Recognition Door Lock using IoT
IRJET - Face Recognition Door Lock using IoTIRJET - Face Recognition Door Lock using IoT
IRJET - Face Recognition Door Lock using IoT
 
Final PPT.pptx
Final PPT.pptxFinal PPT.pptx
Final PPT.pptx
 
Development of anti theft security system
Development of anti theft security systemDevelopment of anti theft security system
Development of anti theft security system
 
Face Recognition System using OpenCV
Face Recognition System using OpenCVFace Recognition System using OpenCV
Face Recognition System using OpenCV
 
Gated Communities Access Control Solution
Gated Communities Access Control SolutionGated Communities Access Control Solution
Gated Communities Access Control Solution
 
Facial Recognition Mini project 3.pdf
Facial Recognition Mini project 3.pdfFacial Recognition Mini project 3.pdf
Facial Recognition Mini project 3.pdf
 
Face Recognition Based Automated Student Attendance System
Face Recognition Based Automated Student Attendance SystemFace Recognition Based Automated Student Attendance System
Face Recognition Based Automated Student Attendance System
 
Attendance management system using face recognition
Attendance management system using face recognitionAttendance management system using face recognition
Attendance management system using face recognition
 
IRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric LearningIRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric Learning
 
IRJET - Smart Doorbell System
 IRJET - Smart Doorbell System IRJET - Smart Doorbell System
IRJET - Smart Doorbell System
 

Kürzlich hochgeladen

Instruct Nirmaana 24-Smart and Lean Construction Through Technology.pdf
Instruct Nirmaana 24-Smart and Lean Construction Through Technology.pdfInstruct Nirmaana 24-Smart and Lean Construction Through Technology.pdf
Instruct Nirmaana 24-Smart and Lean Construction Through Technology.pdfEr.Sonali Nasikkar
 
Theory for How to calculation capacitor bank
Theory for How to calculation capacitor bankTheory for How to calculation capacitor bank
Theory for How to calculation capacitor banktawat puangthong
 
SLIDESHARE PPT-DECISION MAKING METHODS.pptx
SLIDESHARE PPT-DECISION MAKING METHODS.pptxSLIDESHARE PPT-DECISION MAKING METHODS.pptx
SLIDESHARE PPT-DECISION MAKING METHODS.pptxCHAIRMAN M
 
Electrostatic field in a coaxial transmission line
Electrostatic field in a coaxial transmission lineElectrostatic field in a coaxial transmission line
Electrostatic field in a coaxial transmission lineJulioCesarSalazarHer1
 
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...Lovely Professional University
 
How to Design and spec harmonic filter.pdf
How to Design and spec harmonic filter.pdfHow to Design and spec harmonic filter.pdf
How to Design and spec harmonic filter.pdftawat puangthong
 
Software Engineering - Modelling Concepts + Class Modelling + Building the An...
Software Engineering - Modelling Concepts + Class Modelling + Building the An...Software Engineering - Modelling Concepts + Class Modelling + Building the An...
Software Engineering - Modelling Concepts + Class Modelling + Building the An...Prakhyath Rai
 
BURGER ORDERING SYSYTEM PROJECT REPORT..pdf
BURGER ORDERING SYSYTEM PROJECT REPORT..pdfBURGER ORDERING SYSYTEM PROJECT REPORT..pdf
BURGER ORDERING SYSYTEM PROJECT REPORT..pdfKamal Acharya
 
Multivibrator and its types defination and usges.pptx
Multivibrator and its types defination and usges.pptxMultivibrator and its types defination and usges.pptx
Multivibrator and its types defination and usges.pptxalijaker017
 
Artificial Intelligence Bayesian Reasoning
Artificial Intelligence Bayesian ReasoningArtificial Intelligence Bayesian Reasoning
Artificial Intelligence Bayesian Reasoninghotman30312
 
Online crime reporting system project.pdf
Online crime reporting system project.pdfOnline crime reporting system project.pdf
Online crime reporting system project.pdfKamal Acharya
 
Geometric constructions Engineering Drawing.pdf
Geometric constructions Engineering Drawing.pdfGeometric constructions Engineering Drawing.pdf
Geometric constructions Engineering Drawing.pdfJNTUA
 
Introduction to Artificial Intelligence and History of AI
Introduction to Artificial Intelligence and History of AIIntroduction to Artificial Intelligence and History of AI
Introduction to Artificial Intelligence and History of AISheetal Jain
 
Online book store management system project.pdf
Online book store management system project.pdfOnline book store management system project.pdf
Online book store management system project.pdfKamal Acharya
 
Operating System chapter 9 (Virtual Memory)
Operating System chapter 9 (Virtual Memory)Operating System chapter 9 (Virtual Memory)
Operating System chapter 9 (Virtual Memory)NareenAsad
 
EMPLOYEE MANAGEMENT SYSTEM FINAL presentation
EMPLOYEE MANAGEMENT SYSTEM FINAL presentationEMPLOYEE MANAGEMENT SYSTEM FINAL presentation
EMPLOYEE MANAGEMENT SYSTEM FINAL presentationAmayJaiswal4
 
15-Minute City: A Completely New Horizon
15-Minute City: A Completely New Horizon15-Minute City: A Completely New Horizon
15-Minute City: A Completely New HorizonMorshed Ahmed Rahath
 
Insurance management system project report.pdf
Insurance management system project report.pdfInsurance management system project report.pdf
Insurance management system project report.pdfKamal Acharya
 
Lesson no16 application of Induction Generator in Wind.ppsx
Lesson no16 application of Induction Generator in Wind.ppsxLesson no16 application of Induction Generator in Wind.ppsx
Lesson no16 application of Induction Generator in Wind.ppsxmichaelprrior
 
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...Roi Lipman
 

Kürzlich hochgeladen (20)

Instruct Nirmaana 24-Smart and Lean Construction Through Technology.pdf
Instruct Nirmaana 24-Smart and Lean Construction Through Technology.pdfInstruct Nirmaana 24-Smart and Lean Construction Through Technology.pdf
Instruct Nirmaana 24-Smart and Lean Construction Through Technology.pdf
 
Theory for How to calculation capacitor bank
Theory for How to calculation capacitor bankTheory for How to calculation capacitor bank
Theory for How to calculation capacitor bank
 
SLIDESHARE PPT-DECISION MAKING METHODS.pptx
SLIDESHARE PPT-DECISION MAKING METHODS.pptxSLIDESHARE PPT-DECISION MAKING METHODS.pptx
SLIDESHARE PPT-DECISION MAKING METHODS.pptx
 
Electrostatic field in a coaxial transmission line
Electrostatic field in a coaxial transmission lineElectrostatic field in a coaxial transmission line
Electrostatic field in a coaxial transmission line
 
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
 
How to Design and spec harmonic filter.pdf
How to Design and spec harmonic filter.pdfHow to Design and spec harmonic filter.pdf
How to Design and spec harmonic filter.pdf
 
Software Engineering - Modelling Concepts + Class Modelling + Building the An...
Software Engineering - Modelling Concepts + Class Modelling + Building the An...Software Engineering - Modelling Concepts + Class Modelling + Building the An...
Software Engineering - Modelling Concepts + Class Modelling + Building the An...
 
BURGER ORDERING SYSYTEM PROJECT REPORT..pdf
BURGER ORDERING SYSYTEM PROJECT REPORT..pdfBURGER ORDERING SYSYTEM PROJECT REPORT..pdf
BURGER ORDERING SYSYTEM PROJECT REPORT..pdf
 
Multivibrator and its types defination and usges.pptx
Multivibrator and its types defination and usges.pptxMultivibrator and its types defination and usges.pptx
Multivibrator and its types defination and usges.pptx
 
Artificial Intelligence Bayesian Reasoning
Artificial Intelligence Bayesian ReasoningArtificial Intelligence Bayesian Reasoning
Artificial Intelligence Bayesian Reasoning
 
Online crime reporting system project.pdf
Online crime reporting system project.pdfOnline crime reporting system project.pdf
Online crime reporting system project.pdf
 
Geometric constructions Engineering Drawing.pdf
Geometric constructions Engineering Drawing.pdfGeometric constructions Engineering Drawing.pdf
Geometric constructions Engineering Drawing.pdf
 
Introduction to Artificial Intelligence and History of AI
Introduction to Artificial Intelligence and History of AIIntroduction to Artificial Intelligence and History of AI
Introduction to Artificial Intelligence and History of AI
 
Online book store management system project.pdf
Online book store management system project.pdfOnline book store management system project.pdf
Online book store management system project.pdf
 
Operating System chapter 9 (Virtual Memory)
Operating System chapter 9 (Virtual Memory)Operating System chapter 9 (Virtual Memory)
Operating System chapter 9 (Virtual Memory)
 
EMPLOYEE MANAGEMENT SYSTEM FINAL presentation
EMPLOYEE MANAGEMENT SYSTEM FINAL presentationEMPLOYEE MANAGEMENT SYSTEM FINAL presentation
EMPLOYEE MANAGEMENT SYSTEM FINAL presentation
 
15-Minute City: A Completely New Horizon
15-Minute City: A Completely New Horizon15-Minute City: A Completely New Horizon
15-Minute City: A Completely New Horizon
 
Insurance management system project report.pdf
Insurance management system project report.pdfInsurance management system project report.pdf
Insurance management system project report.pdf
 
Lesson no16 application of Induction Generator in Wind.ppsx
Lesson no16 application of Induction Generator in Wind.ppsxLesson no16 application of Induction Generator in Wind.ppsx
Lesson no16 application of Induction Generator in Wind.ppsx
 
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
 

Facial Recognition Door unlock using Machine Learning.

  • 1. Facial Recognition Door Unlock Submitted in the partial fulfilment for the award of the degree of BACHELOROF ENGINEERING IN Computer Science and Engineering with Specialization in Artificial Intelligence and Machine Learning Submitted by: Sagar Vashist 21BCS6597 Yuboraj Ganguly 21BCS6602 Sameesh Bagga 21BCS6623 Under the Supervision of: Mrs. Rajat Tiwari
  • 2. With the rise of smart home technology, many are looking for ways to increase the security and convenience of their homes & property. One potential solution is a facial recognition door unlock system, which uses advanced technology to grant access to authorized users. Facial recognition technology has become increasingly sophisticated in recent years, thanks to advances in artificial intelligence and machine learning. These systems can now accurately recognize individuals based on facial features, even in challenging lighting conditions or from unusual angles. In addition to providing a high level of security, a facial recognition door unlock system can also be very convenient for users. They don't need to remember a code or carry a key; instead, they can simply approach the door and be granted access automatically. Introduction
  • 3. This project aims to explore the potential of facial recognition technology for home security, by building a prototype facial recognition door unlock system. We will use a combination of hardware and software tools to create a system that can accurately recognize authorized users and grant them access to a locked door. While facial recognition technology has many potential benefits, it's also important to consider the potential risks and challenges. We will take a comprehensive approach to security and privacy, using advanced encryption and ensuring that user data is protected at all times. Ultimately, the goal of this project is to create a secure and convenient facial recognition door unlock system that can be used in real-world applications. By demonstrating the potential of this technology, we hope to inspire further innovation in the field of smart home security.
  • 4. Problem Formulation 1. Security: One of the primary reasons for implementing facial recognition technology is to enhance security measures. Facial recognition can be a highly secure way to authenticate and grant access to a restricted area or building. 2. Convenience: Facial recognition can offer a convenient alternative to traditional key or card-based entry systems. Users can simply walk up to the door and be granted access without the need for any physical keys or access cards. 3. Accuracy: Facial recognition technology has become highly accurate in recent years, making it a reliable means of authentication. This can help prevent unauthorized access and improve security. 5. Cost-effectiveness: Facial recognition technology can be a cost-effective solution in the long run, as it eliminates the need for physical keys and access cards. Additionally, it can reduce the need for security personnel to monitor access points. 6.User-friendly: Facial recognition technology is user-friendly, as users don't need to carry anything extra to gain access. This can improve the overall user experience and reduce frustration associated with lost or forgotten access cards. Overall, a facial recognition door unlock project can offer a highly secure, convenient, and cost-effective solution for access control, making it a compelling option for a wide range of settings.
  • 5. Objectivesof the Work 02 Ensure that the system is secure and cannot be easily bypassed by unauthorized users, through measures such as encryption, user authentication, and anti- spoofing techniques. 03 Test the system thoroughly to ensure that it works reliably in a range of lighting conditions, with different camera angles and distances, and with a variety of facial features and expressionsud technology. 01 Develop a facial recognition system that can accurately identify authorized individuals and grant them access to a locked door. 04 Evaluate the system's accuracy and speed of recognition, and optimize its performance through machine learning and other techniques. 05 Document the project thoroughly, including its design, implementation, testing, and evaluation, so that others can replicate or build upon the work in the future.
  • 6. Methodology used The methodologies in this project will include hardware and software development and integration of both. The hardware development will involve selecting and integrating a low-cost camera, microcontroller, and locking mechanism. In this algorithm will take a few images from different angles and then check if the user is registered. The software development will involve developing facial recognition algorithms, image processing, and database management. The integration will involve testing and optimizing our system for accuracy, speed, and reliability
  • 7. The training of a face-unlocking CNN involves feeding it thousands of images of faces from a variety of angles, lighting conditions, and expressions. One such system is the Face Net system developed by Google, which uses a deep convolutional neural network (CNN) to extract facial features and then applies a distance metric to determine the similarity between two faces. Another system is the Deep Face system developed by Facebook, which uses a deep neural network to extract facial features and then applies a SoftMax classifier to classify the faces. Therefore, there is a need for an alternative algorithm that can provide high accuracy with low computational costs. Use of CNN
  • 8. Convolutional layer: Activation layer: Pooling layer: Fully Connected Layers: Batch Normalization layer: CNN L CN ayers
  • 9.
  • 10. According to the evaluation, the facial recognition system achieved an overall accuracy of 95%. This indicates that the system was able to recognize the person correctly in most cases. The FAR was found to be 2%, indicating low susceptibility to fraudsters. The FRR is 3%, indicating that the system correctly identified the matching faces with high accuracy. Determines whether it is an authorized person or not based on the pre-registered for pre-stored images in the database Results
  • 11. Basedon the results of the tests that havebeen carried out, it can be concluded that the system runs as expected and can be used as a facial recognition-based automatic door lock system. When the facial image cannot be recognized or is unsuccessful in being identified, the door will remain closed. Therefore, the system can beinstalled asasecurityfeature on adoor to aprivate room. The latest development of 3D sensors points to a new approach to facial recognition that may be able to get through the primary obstacles, such as changes in physical appearance, the ageing process, position, changes in light intensity, and more generally, facial emotions, missing data, cosmetics, and occlusions. In the event of problematic acquisition settings, the geometry information offered by facial datasets could greatly increase the accuracy of facial identification. Results
  • 12. Based on the results of the tests that have been carried out, it can be concluded that the system runs as expected and can be used as a facial recognition-based automatic door lock system. When the facial image cannot be recognized or is unsuccessful in being identified, the door will remain closed. Therefore, the system can be installed as a security feature on a door to a private room. The latest development of 3D sensors points to a new approach to facial recognition that may be able to get through the primary obstacles, such as changes in physical appearance, the ageing process, position, changes in light intensity, and more generally, facial emotions, missing data, cosmetics, and occlusions. In the event of problematic acquisition settings, the geometry information offered by facial datasets could greatly increase the accuracy of facial identification. Conclusion Highlights 1. Facial recognition technology can provide a convenient and secure way to unlock doors, eliminating the need for keys or access codes. 2. Using a camera to capture an image of the user's face, the software can compare it to a database of authorized users to determine if access should be granted. 3. This technology can be especially useful in high-security environments such as government buildings, research facilities, or financial institutions. 4. By integrating facial recognition with other security systems such as alarms and cameras, the door unlock project can provide a comprehensive security solution
  • 13. Conclusion Pitfalls Facial recognition technology has come under criticism for potential biases, inaccuracies, and privacy concerns. It is essential to consider these issues when implementing the technology and ensure that the system is fair and transparent. The accuracy of facial recognition technology can be affected by various factors such as lighting, angles, and facial expressions. The system may fail to recognize authorized users, resulting in frustration and inconvenience. It is crucial to implement proper security protocols to prevent unauthorized access to the facial recognition system itself, as this can compromise the entire security system. Finally, the cost of implementing a facial recognition door unlock project can be significant, requiring hardware, software, and ongoing maintenance expenses. A cost-benefit analysis should be conducted to ensure that the benefits of the project justify the investment.
  • 14. Improved accuracy: As facial recognition technology continues to advance, there will likely be further improvements in accuracy, particularly in challenging lighting conditions or with subjects wearing masks or other face coverings. Scalability: Currently, most facial recognition systems are designed to work with a relatively small number of users. In the future, it may be possible to scale up the system to work with larger groups of people, potentially making it useful for access control in public spaces. Multi-factor authentication: While facial recognition can be an effective way to authenticate users, it may be even more secure to combine it with other forms of authentication, such as passwords or biometric data from other parts of the body (such as fingerprints or iris scans). Privacy concerns: Facial recognition technology has come under scrutiny due to concerns about privacy and potential misuse. Future developments in this area may focus on ways to mitigate these concerns, such as incorporating encryption or anonymization techniques. Future Scope
  • 15. References [1]. O. Deniz, M. Castrillon, M. Hernandez, “Face recognition using independent component analysis and support vector machines,” Pattern Recognition Letters, vol. 24, pp. 2153-2157, 2003. [2]. I.J. Cox, J. Ghosn, and P.N. Yianios, “Feature-Based face recognition using mixture-distance,” Computer Vision and Pattern Recognition, 1996. [3]. M. Turk and A. Pentland, “Eigenfaces for recognition,” J. Cognitive Neuroscience, vol. 3, pp. 71-86, 1991. [4]. Ho-Man Tang, Michael Lyu, and Irwin King, "Face recognition committee machine," In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2003), pp. 837- 840, April 6-10, 2003 [5]. "Design and Implementation of a Facial Recognition Door Lock System" by D. D. Yang, D. Y. Lee, and J. H. Kim -Link: https://www.mdpi.com/1424- 8220/19/13/3009 [6]."Smart Door Lock using Facial Recognition System" by S. Senthil Kumar, S. Sathish Kumar, and S. Sivakumar. (https://ieeexplore.ieee.org/document/9041969) [7]. "Facial Recognition Door Lock Security System using IoT" by M. B. Khan, M. A. Al-Garadi, and A. R. Khan. (https://www.mdpi.com/2504- 3900/25/1/29) [8]. "Facial Recognition-Based Door Lock System Using Deep Learning" by H. M. Elhoseny, M. A. M. Mahmoud, and S. M. Riad. (https://www.mdpi.com/1424-8220/20/23/6765)