Scribd
Upload
54 views15 pages

Zeroth Review

This document presents a proposal for an AI-powered facial recognition system for smart home security. The system would use a camera and monitor at the front door to identify individuals and control access. A literature review covers existing works on visitor authentication, wireless vision sensor networks, multispectral facial recognition, and hierarchical neural networks for face recognition in smart locks. The proposed solution would extract facial features from video clips and images using CNN algorithms. It would include modules for face registration, mask detection, face classification, and an alert system. The system aims to provide improved security over password-based methods by leveraging biometric facial recognition.

Uploaded by

4022 MALISHWARAN M
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
54 views15 pages

Zeroth Review

This document presents a proposal for an AI-powered facial recognition system for smart home security. The system would use a camera and monitor at the front door to identify individuals and control access. A literature review covers existing works on visitor authentication, wireless vision sensor networks, multispectral facial recognition, and hierarchical neural networks for face recognition in smart locks. The proposed solution would extract facial features from video clips and images using CNN algorithms. It would include modules for face registration, mask detection, face classification, and an alert system. The system aims to provide improved security over password-based methods by leveraging biometric facial recognition.

Uploaded by

4022 MALISHWARAN M
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 15

AI POWERED AUTHENTICATION FOR SMART

HOME SECURITY
Presentation by
ELIZAJOHN A (920219104013)
HARIHARAN T (920219104016)
MALISHWARAN M (920219104022)
SRIRAM V (920219104045)
Guided by
Mrs. S.SUGANYA B.E,M.E,
Assistant Professor/CSE

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING


ANNA UNIVERSITY :: CHENNAI 600 025

Date : 1
Abstract
For face recognition in surveillance scenarios, identifying a
person captured on image or video is one of the key tasks.
Human beings are recognized by their unique facial
characteristics. In the face recognition approach, a given
face is compared with the faces stored in the database in
order to identify the person. In our proof of concept of a
smart door we have used a live camera on the front side of
setup attached to a display monitor connected with the
camera to show who is standing in front of the door, also
the whole system will be able to give alert to the owner.
Literature survey
S. Title of the paper Authors Novelty Results
No & year
1 Design for Visitor hyung-jin Designed a system Implementation
Authentication mun, based on deep learning with hardware
Based on Face min-hye technology that recognizes cost is very high
Recognition lee, and authenticates the face
Technology Using 2022 of
CCTV a user during the visitor
access process and controls
user access.

2 Design of Wireless Tsung-han WVSN has been Sensor based


Vision Sensor tsai implemented for the smart motion detection
Network for Smart 2020 home, which includes the so cost is very
Home features of the VSN and the high to implement
server
Literature survey
S. Title of the paper Authors & Novelty Results
No year
3 Multispectral Facial Luís lopes Multispectral facial Only support the
Recognition: A chambino, recognition methods image datasets
Review 2020 achieve better
performance when
compared to facial
recognition systems

4 Face Recognition Muhammad Proposed a hierarchical Less efficiency in


for Smart Door Waseem, classification network recognition
Lock System using 2020 based on two-tier performance
Hierarchical recognition systems
Network
Literature survey
S. Title of the paper Authors & Novelty Results
No year
5 Comparison Min-hye Necessary to select an Does not
Analysis and Case Lee, 2020 appropriate algorithm implemented in real
Study for Deep in various fields time environments
Learning-based requiring object
Object Detection detection technology
Algorithm
6 Real-Time Face Xinbei Fast and accurate mask Support only facial
Mask Detection Jiang, 2021 detector with a channel image datasets and
Method Based on attention mechanism video datasets
YOLOv3
Existing system
 We are facing security issues in every aspect. So, we have
to resolve these issues by using streamlined technology.
 The most important characteristic of any home security
system is to discover the people who enter or leave the
house.
 Instead of monitoring that through passwords or pins,
unique faces can be made use of as they are one’s
biometric characteristics.
Problems or constraints in the
existing system
 Fail to simultaneously utilize the rich information and
relationship between still images
 Just execute image to image matching
 Performance is less at the time of face recognition
 Need large number of dataset
 Need hardware system
Proposed solution
 Design the application for face recognition from Video clips
to still images.
 While it is generally possible to do recognition from video
sequences, the training process is usually done over still
images.
 Using Grassmann manifold learning method to construct
subspaces in between to find connections between the still
images and video clips.
 Implement CNN algorithm to classify the faces as known or
unknown.
 Provide alert and SMS alert at the time of unknown samples
prediction and also alert user to remove the mask, if the
person wear it.
SPECIFICATIONS
HARDWARE REQUIREMENTS
•Processor : Intel processor
•RAM : 1GB
•Hard disk : 160 GB
•Compact Disk : 650 Mb
•Keyboard : Standard keyboard
•Monitor : 15 inch color monitor
SPECIFICATIONS
SOFTWARE REQUIREMENTS
•Operating system : Windows OS
•Front End : PYTHON
•Back End : MYSQL
•IDE : PYCHARM
Architecture diagram/Flowchart

Facial features matching with


CNN algorithm
MODULES
• Framework Construction
• Face Registration
• Mask Detection
• Face Classification
• Alert System
References
• Hyung-jin mun and Min-hye lee “Design for Visitor
Authentication Based on Face Recognition Technology
Using CCTV.” IEEE Access, vol. 10 (2022): 124604 - 124618

• Tsai, Tsung-Han, et al. "Design of wireless vision sensor network


for smart home." IEEE Access 8 (2020): 60455-60467.

• L. L. Chambino, J. S. Silva, and A. Bernardino, ‘‘Multispectral


facial recognition: A review,’’ IEEE Access, vol. 8, pp. 207871–
207883, 2020
References
• Waseem, Muhammad, et al. "Face recognition for smart door
lock system using hierarchical network." 2020 International
Conference on Computational Intelligence (ICCI). IEEE, 2020.

• Lee, Min-hye, and Hyung-Jin Mun. "Comparison analysis and


case study for deep learning-based object detection
algorithm." Int. J. Adv. Sci. Converg 2.4 (2020): 7-16.

• Jiang, Xinbei, et al. "Real-time face mask detection method


based on YOLOv3." Electronics 10.7 (2021): 837.
THANK
YOU

You might also like