1. FACIAL RECOGNITION SMART GLASSES FOR VISUALLY
CHALLENGED PEOPLE
Dept.of ECE
GITAM School of Technology
GITAM, Bengaluru-561203
(DEEMEDTO BE UNIVERSITY)
Student Roll. No.:
321910402019 - M.Vamsi Krishna
321910402022 - Sameeulla Khan
321910402037 - M.Vishnu Vardhan Reddy
321910402048 - R.Lavanya
Guided by:
Dr. Karthigai Pandian M
Associate Professor
Department of EECE
GITAM School of Technology
Bengaluru- 561203
2. Contents
• Abstract and Introduction
• Literature survey
• Block diagram and Methodology
• Hardware and Software
• Objectives and Applications
• References
3. Abstract:
➢ In this project, we are making a prototype of a smart eyeglass that helps visually
challenged people to recognize the person in front and also to learn about obstacles
ahead.
➢ This is enabled by Raspberry pi which is a hardware processor that takes images
from the camera and compares with the available database.
➢ If a match is found with the database, it will inform the name of person.
➢ If image is not in the database it will tell that it is an unknown person.
➢ And object detection is achieved using the ultrasonic sensor (i.e., it sends a sound
wave and sound wave is reflected back if any object is encountered).
➢ Other components involved are Pi camera, 5V battery, glasses, USB cable and
wires.
4. INTRODUCTION:
➢ People with visual impairment face various problems in their daily life as the
modern assistive devices are often not meeting the consumer requirements in term
of price and level of assistance. This project presents a new design of assistive
smart glasses for visually impaired persons.
➢ The objective is to assist in multiple daily tasks using the advantage of wearable
design format.
➢ The aim is to employ computer vision for recognition of persons and the
surrounding practiced by the blind on a daily basis.
➢ The camera is placed on the blind person's glasses. A dataset of persons gathered
from daily scenes is created to achieve the required recognition.
➢ The proposed method for the blind aims at expanding possibilities to people with
vision loss to achieve their full potential.
6. REF.
NO
Title of paper Abstract Outcome Methodology Research gap
1.
Hot Glass - Human Face,
Object And Textual
Recognition For Visually
Challenged
The design involves
human face, object
and textual
recognition which
make vision for
visually challenged.
Human Face
recognition, Object
recognition and Text
to speech conversion
Face recognition-
PCAAlgorithm.
Object Recognition-
SIR
Text Recognition-
OCR
The camera
can’t capture
360 degrees
2.
Arduino based Customized
Smart Glasses for the Blind
People
Smart aid techniques
for obstacle detection
with the fire detection
and also the
background detection.
We have developed a
low-cost solution
using the input and
output sensors
connected through
Arduino board.
Obstacle , fire and
background detection
Obstacle
detection-
Ultrasonic sensor
Fire detection –
smoke sensor
Background
detection-LDR
Object and face
recognition
7. REF.
NO
Title of paper Abstract Outcome Methodology Research gap
3.
Assistive Technology for
Integrating the Visually
Impaired in Mainstream
Education and Society
Assistive technology
tool, the system
comprises of smart
glasses, processing
unit and smart phone
application;. The
features are
developed to facilitate
VI with reading in
English and Arabic,
in-door navigation
and face recognition
Face recognition,
Reading of Arabic
and Indoor
navigation.
Face recognition-
OpenCV
Reading of
Arabic-OCR
Indoor
Navigation-
NRF24101+
module
Indoor
navigation can
be done by
image
processing
4.
Real-Time Family Member
Recognition Using
Raspberry Pi for Visually
Impaired People
This research work
firstly describes the
development and
estimation of
raspberry pi based
smart glass system to
recognize the family
members.
Identification of
family members.
Face recognition-
Image processing
Proper
identification is
not achieved
8. REF.
NO
Title of paper Abstract
Outcome
Methodology Research
gap
5.
Smart Glasses For Visually
Impaired People With Facial
Recognition
Our research describes the
design and development of
raspberry pi based smart
glasses with face recognition
and voice assistant. This idea
helps them to recognize
people around them even
when their known person is
not talking and also it has
some cool features like
playing songs, browsing etc.
Face
recognition
and hot word
detection
Face recognition-
open cv
Hot word
detection-
Porcupine
Camera could
not be
continuously
kept in On
condition.
6.
A New Method For
Recognition And Obstacle
Detection For Visually
Challenged Using Smart
Glasses Powered With
Raspberry Pi
In this paper, we are
presenting an electronic
device for obstacle detection
and face recognition to assist
visually challenged people.
The device is in the form of
smart glasses that has
ultrasonic sensor, pi camera
and raspberry pi installed on
it.
Face
recognition
Face recognition -
OpenCV
Very less
storage
9. REF.
NO
Title of paper Abstract Outcome Methodology Research
gap
7.
Smart Glasses for
Visually Impaired
Person
The paper presents a
prototype of smart glass
that can recognize and
detects object using
raspberry pi.
Obstacle detection
and
Face recognition
Face recognition-
OpenCV
Object detection-
Ultrasonic sensor
When a person
is in between
two ultrasonic
sensors, it is
not detecting
the person
8.
Motion based smart
assistant for visually
impaired people
The smart assist help
impaired people in
mobility with
confidence by
realizing the nearby
objects.
Face recognition,
exact location,
mobile
communication
Face recognition –Open
CV
Location-GPS
Mobile communication-
GSM
Size of device
is very large
10. REF
NO.
Title of paper Abstract Outcome Methodology Research gap
9.
Crosswalk Guidance
System for the Blind
Street crossing can be a
significant challenge for
visually impaired people,
limiting their mobility
especially in urban
environments. To date, there
are few solutions for this
significant problem. Current
approaches for guiding blind
pedestrians in crosswalks
have mainly focused on
detection of crosswalks and
crosswalk signals
Detecting traffic
signals and road
crossing
ROI tracker, CNN
classifier,
Proper aiming
of the camera
was difficult due
to magnified
camera settings
and lack of
visual feedback
11. Outcome of Literature Survey
The scope of the proposed project includes
1. Improving the memory to store in the database.
2. Reducing the amount of hardware components.
3. Increasing the angle and aiming of the camera.
4. Improving the accuracy of the detection of people.
12. BLOCK DIAGRAM AND METHODOLOGY
It will tell name
of the person
Images are stored
in database
Unknown
person
13. It tell the name of the
person through ear
phones when there is
matching with data set
Raspberry Pi
Pi camera capture
Ultrasonic sensor
It will tell object is
there when the
ultrasonic sensor
measures object
distance is below
threshold
16. Thonny:
IDE stands for Integrated Development Environment. It's a coding tool
which allows us to write, test, and debug our code in an easier way, as
they typically offer code completion or code insight by highlighting,
resource management, debugging tools,…etc.
SOFTWARE USED
17. Work carried out so far and Result
• We are working on the assembling the components as per the requirements.
• We have worked on the hardware components to understand how to
measure distance using ultrasonic sensor and capturing of images using Pi
cam.
18. REFERENCES:
1. Diwakar Srinath A", Praveen Ram A.R2, Siva R", Kalaiselvi V.K.G", Ajitha G “Hot Glass - Human Face, Object And
Textual Recognition for Visually Challenged” - 2017 Second International Conference On Computing and
Communications Technologies(ICCCT 17).
2. Mohammed Noman, Wessam Shehieb & Tazeen Sharif “Assistive Technology for Integrating the Visually Impaired in
Mainstream Education and Societ” -2019 Advances in Science and Engineering Technology International Conferences
(ASET).
3. Sanjay Kumar Y R, Nivethetha T, Priyadharshini P ” Smart Glasses For Visually Impaired People With Facial
Recognition”- 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT).
4. Md. Tobibul Islam, Mohiuddin Ahmad, Akash Shingha Bappy “Real-Time Family Member Recognition Using
Raspberry Pi for Visually Impaired People”- 2020 IEEE Region 10 Symposium (TENSYMP), 5-7 June 2020, Dhaka,
Bangladesh.
5. Prathima Samuda , Praveena N G , Nithiya C “Arduino based Customized Smart Glasses for the Blind People” -
Proceedings of the Second International Conference on Artificial Intelligence and Smart Energy (ICAIS-2022) IEEE
Xplore Part Number: CFP22OAB-ART; ISBN: 978-1-6654-0052-7 .
6. K. Sundar Srinivas, K. Sahithya, G. Lakshmi Tejaswi, K. Hari Gopal, B. Pavan Karthik “A New Method For
Recognition And Obstacle Detection For Visually Challenged Using Smart Glasses Powered With Raspberry Pi”-
International Journal of Engineering Applied Sciences and Technology, 2020 Vol. 5, Issue 1, ISSN No. 2455-2143,
Pages 408-412 Published Online May 2020.