GLOVE BASED GESTURE RECOGNITION USING IR SENSOR

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 03 | Mar 2023 www.irjet.net p-ISSN: 2395-0072
© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 120
GLOVE BASED GESTURE RECOGNITION USING IR SENSOR
J. Bharath Krishnaa1, R. Haritha2, G.D. Haritha3, J. Shri Lekha4, S.R. Malathi5
12345
Department of Electronics and Communication Engineering, Sri Venkateswara College of Engineering,
Sriperumbudur, Tamil Nadu
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - In recent times, thanks to the support of cutting-
edge technology interfaces, the development of hand gesture
recognition systemshasdrawngreaterattention. Additionally,
sign language recognition was primarily created to aid in
communication betweendumband deafpeople. Variousimage
processing approaches, includingsegmentation, optimization,
and classification, are used in conventional worksto recognize
hand gestures. Although it takes more time to recognize
patterns, there are fewer false positives, higher error rates,
and incorrect computation outputs as a result of the primary
issues with inefficientprocessingofhuge dimensionaldatasets.
Therefore, the goal of this project is to create aneffectivehand
gesture recognition system employing an inexpensive but
effective IR sensor that is integrated into the gloves. The light
obtained by the IR sensor, which is positioned across from the
light emitting diode, is used to recognize thehand gesture. The
LCD screen shows the hand gesture's meaning, and an audio
message is also played through the speaker. Comparing the
suggested method to the current ones reveals that it is more
accurate and has a lower error rate. People with
communication impairments have more interaction and
security difficulties. The importance of this endeavour resides
in finding solutions to these issues. Bypushingabuzzerbutton,
the suggested smart speaking glove can notify users of alerts
and their current location. Our main goal is to address both
the safety-related and communication-related problems. The
proposed system's experimental results show that both have
been accomplished. The gap between normal people and
speech-impaired persons will be greatly improved by
implementing the same method in real-time apps.
Key Words: GSM & GPS module, Arduino Nano, Hand
gesture recognition, Speaker & Display output, IR
sensor.
1.INTRODUCTION
The World Federation of the DeafandtheWHOestimatethat
70 million persons worldwide are bothdeafandmute.There
are 300 million people in the globe, 32 million of whom are
deaf. Most people with speech and hearing issues cannot
read or write in commonly used languages. In order to
communicate with others, deaf and mute people utilise sign
language (SL), which is their native speech. More often than
speaking, gestures in sign languages—including the use of
finger movements, hand motions, and facial expressions—
are used to convey messages. This project's major goal is to
make it possibleforhearingandspeech-impairedindividuals
to communicate in real time. Hardware and software are
combined to createtechnologies.Hardwareandsoftware are
combined to create technologies. Before producing speech
and a display, the device will use the micro-controller to
process human gesture input. The only method to share our
opinions is through communication. It isnotanticipatedthat
this will limit them in any manner. As a result, those who are
deaf and dumb find it difficult to communicate with others,
so it is crucial to create a model that is both practical and
appropriate for them. As a result,weprimarilycommunicate
through hand gestures and a tool called SMART SPEAKING
GLOVE. This technology uses an embedded IR sensor in
gloves to enable and detect hand gesture recognition.This is
accomplished by measuring the quantity of light that strikes
the receiver, which is positioned in front of the transmitter,
and conveying the meaning of the hand gesture in the form
of an output in the form of a display and voice. People with
speech impairments have trouble verbally speaking,
whereas those with hearing impairments have trouble
hearing what other people are saying. Both communication
and safety-related issues are our focus. Speech-impaired
people must deal with both problems as a result, which is
where our smart speaking glove comes in. In the actual
world, using this glove will bebothimmenselyadvantageous
and demanding. The deaf and dumb have more security
challenges than social contact problems. This project's
originality derives from resolving this problem.
2. LITERATURE REVIEW
In their study described in [1], A. Z. Shukor et al focused-on
individuals who are deaf and mute, emphasizing their
reliance on sign language for communication. However,
communicating with non-sign language users poses a
significant challenge for them, particularly in educational,
social, and work environments. To address this issue, the
researchers aimed to develop a sign language translation
system that would facilitatecommunicationbetweenhearing
or speech-impaired individuals and those who do not
understand sign language. Additionally, they sought to
evaluate the accuracy of this system in interpreting sign
language. The sign language translation system they
developed utilized a data glove configuration.Itincorporated
10 tilt sensors to capture finger flexion, an accelerometer to
detect hand motion, a micro-controller, and a Bluetooth
module to transmit interpreted information to a mobile
phone. The researchers conducted several experiments to
assess the performance of the tilt sensors and the overall

accuracy of the data glove in translating selected alphabets,
numbers, and words from the Malaysian Sign Language. The
results of the initial experiment indicatedthatthetiltsensors
required tilting beyond 85 degreestosuccessfullychangethe
digital state. In terms of accuracy, when tested by four
individuals, the data glove achieved an average accuracy of
95% for translating alphabets, 93.33% for numbers, and
78.33% for gestures. The overall average accuracy for
translating all types of gestures was 89%. The researchers
suggested that further improvements could be made by
incorporating additional training and test data and utilizing
underlying frameworks such as Hidden Markov Models. In
summary, the study presented by A. Z. Shukor et al aimed to
develop asign language translationsystemusingadataglove
configuration. Their findings demonstrated promising
accuracylevelsfortranslatingselectedelementsofMalaysian
Sign Language. Furtherrefinementsandenhancementscould
be explored in the future to improve the system's
performance.
In their study described in [2], Anbarasi Rajamohan et al
addressed the challenging task of communication between
deaf-mute individualsandthosewhocanhearandspeak.The
researchers aimed to develop a glove-based deaf-mute
communication interpreter system to facilitate
communication for theseindividuals.Thegloveutilizedinthe
system was equipped with five flex sensors, tactile sensors,
and an accelerometer.Eachspecificgestureperformedbythe
user resulted in a proportional change in resistance
measured by the flex sensors, while the accelerometer
detected the orientation of the hand. The processing of these
hand gestures wascarriedoutusingArduino,apopularopen-
source electronics platform.The glovefeaturedtwomodesof
operation: a training modedesignedtobenefiteveryuserand
an operational mode for real-time communication. In the
training mode, users could teach the system their specific
gestures, allowing for personalized communication. The
system concatenated the recognized gestures to formwords,
utilizing the Arduino platform. Furthermore, theresearchers
incorporated a text-to-speech conversion (TTS) block in the
system, enabling the translation of the matchedgesturesinto
voice output. Overall, the project aimed to develop a glove-
based deaf-mute communication interpreter system to
facilitatecommunication between deaf-muteindividualsand
those who can hear and speak.Theglove'ssensors,combined
with Arduino processing,allowedforgesturerecognitionand
the formation of words. The addition of a text-to-speech
conversion block enabled thesystem to providevoiceoutput
corresponding to the recognized gestures.
In their study described in [3], Gunasekaran K. et al focused
on utilizing advancements in embedded systems to design
and develop a sign language translator system aimed at
assisting individuals who are unable to speak (referredtoas
"dumb" in the paper). The primary objective of thisresearch
was to enhance the lifestyle of individuals with speech
impairments. Some individuals around the world often use
sign language as a means of communication, but
understanding sign language can be challenging for the
general population. To address this issue, the researchers
developed a real-time sign language translation system.
When the system detects a sign languagegesture,itplaysthe
corresponding pre-recorded voice, thereby reducing the
communication gap between dumbindividualsandordinary
people. The proposed model consists of four main modules:
the sensing unit, processing unit, voice storage unit, and
wireless communication unit. The researchers integrated
flux sensors and an APR9600 module with the PIC16F877A
microcontroller. The flux sensors, placed in gloves, respond
to hand gestures. Based on the sensor's response, the
microcontroller plays the appropriate recorded voice using
the APR9600 module. The study discusses a snapshot of the
entire system, advantages over existing methods, and
simulation outputs of the process. The proposed system is
highlighted for its high reliability and fast response, offering
potential benefits in bridging the communication gap
between dumb individuals and the general population.
In their study described in [4], H. Ikeda et al presenteda sign
language editing apparatus. This apparatus is designed to
facilitate the creation and display of sign language
animations based on finger movements. The apparatus
consists of several components. Firstly, there is a glove-type
sensor that converts finger movements in sign language into
electrical signals, generating time series data representing
sign language words. This sensor captures the motion of the
fingers and translates it into a usable format. Next, there is a
sign language word data editingdevicethatreceivesthetime
series data from the glove-type sensor and adds additional
predetermined data to process the inputted data. This
editing device modifies the time series data of sign language
words according to specific requirements. The system
includes a sign language word dictionary, which stores the
processed time series data of sign language words. This
dictionary acts as a repositoryforthemodifiedsignlanguage
word data. To create sign language sentences, a sign
language sentence data editing device reads the time series
data of sign language words from the dictionary based on
predetermined characters inputted via an input unit. This
device adds additional information to the time series dataof
sign language words, resulting in time series data
representing complete sign language sentences. A sign
language animation synthesizingdevicetakesthetimeseries
data of sign language sentences produced by the sentence
data editing device as input. It uses this data to generatesign
language animations that depict the movement of the sign
language being expressed. Finally, a display unit is used to
showcase the sign languageanimationsproduced bythesign
language animation synthesizing device. Overall, this sign
language editing apparatus provides a means to convert
finger movements in sign language into digital data, editand
combine that data to formcompletesignlanguagesentences,
and synthesize sign language animations for display.

In their study described in [5], Laura Dipietro et al focused
on the acquisition of hand movementdata usingglove-based
systems and its applications across various engineering
disciplines and biomedical sciences. The paper provides a
comprehensive survey of these glove systems, analysing
their characteristics, technological advancements, and
limitations, while also discussing the current trends in
research. Hand movement data acquisition hasbeenutilized
in numerous fields, including gesture analysis and
biomedical research, making glove-based systems a
prominent tool for capturing such data. Despite being in
existence for over three decades, these systems continue to
attract the interest of researchers from diverse fields. The
primary objective of the paper is to offer readers, both
newcomers and specialists, a comprehensiveunderstanding
of glove system technology and its wide range of
applications. For newcomers to the field, it provides a solid
foundation for comprehending the technology and its
potential applications. Specialists in the field can gain
insights into the breadth of applications in engineering and
biomedical sciences,along withanupdatedunderstandingof
the advancements and frontiers of research in glove-based
systems. By examining the evolution of glove technology,
discussing the various applications, and highlighting the
current limitations and research trends, the study aims to
provide a valuable resource that enhances the
understanding and utilization of glove systems in different
domains of engineering and biomedical sciences.
In their study described in [6], M. G. Kumar et al addressed
the communication challenges faced by speech-impaired
individuals when interacting with those who can speak. As
speech-impaired individuals rely on sign language for
communication, there is a significant communication gap
between them and the general population. To bridge this
gap, the researchers focused on gesture recognition, which
can be accomplished using two approaches: image
processing-based and sensor-based. The project's objective
was to design a smart glove that translates sign language
into text, facilitating easier communication for speech-
impaired or hearing-impaired individuals. The smart glove
was designed to detect and measure finger movements and
the occurrence of contact between the fingers. The sensed
data from the sensors embedded in the glove was processed
by an Arduino UNO board. The processed data was then
transferred to an Android phone using a Bluetooth module.
The transmitted data took the form of text, representing the
sign language gestures. To further enhance communication,
the text data was converted into speech using the Google
Text-to-Speech converter or a similar technology. Overall,
the project aimed to develop a smart glove for sign language
translation, enabling speech-impaired or hearing-impaired
individuals to communicate more easily. By detecting and
translating finger movements into text and converting the
text into speech, the smart glove provided a means for
speech-impaired individuals to communicate with others
effectively.
In their study described in [7], MadhuriYetal focusedonthe
automatic translation of Indian sign language into English
speech to facilitate communication between hearingand/or
speech impaired individuals and those who can hear. The
aim of the research was to develop a system that couldserve
as a translator for people who do not understand sign
language, eliminating the need for an intermediate person
and enabling communication using the natural mode of
speaking.The proposed system is an interactive application
program implemented using LABVIEW software and
integrated into a mobile phone. The mobile phone's built-in
camera is utilized to capture images of sign language
gestures. Vision analysis functions are performedwithin the
operating system, and the resulting speech output is
produced through the device's built-in audio capabilities.
This approach minimizes the need for additional hardware
and reduces expenses. The system incorporates parallel
processing, which helps reduce the lag time between sign
language input and translation. This parallel processing
enables almost instantaneous recognition and translation of
finger and hand movements. The system specificallyfocuses
on recognizingone-handedsignrepresentationsofalphabets
(A-Z) and numbers (0-9). The results of the study
demonstrate high consistency, reproducibility, and a
relatively high level of precision and accuracy.Theproposed
system shows promising performance in translating Indian
sign language into English speech, allowing for effective
communication between hearing and speech impaired
individuals and those who can hear and speak.
In their study described in [8], MohdYusofRahiman Wan
Abdul Aziz et al aimed to develop a system capable of
detecting and recognizing hand gestures from images
captured by a camera. The system was built using Alters
FPGA DE2 board, which features a Nios II soft-core
processor. The implementation involved utilizing image
processing techniques and a simple yet effective algorithm.
Image processing techniques were employedto enhancethe
captured image, enabling smoother subsequent processes
for translating the hand sign signal. The algorithm was
designed specifically for translating numerical hand sign
signals, and the results were displayed on a seven-segment
display. To construct the system, Alters Quartus II, SOPC
Builder, and Nios II EDSsoftware wereutilized.SOPCBuilder
facilitated the interconnection of components on the DE2
board in an efficient and organized manner, reducing the
need for lengthy source code and saving time.QuartusIIwas
responsible for compiling and downloadingthedesignto the
DE2 board. The project also involved equipping a glove with
various sensors, including flex sensors, an accelerometer,
and touch sensors, to detect differentsignlanguagegestures.
Flex sensors were placed on the fingers to measure finger
bending, while an accelerometeronthepalmdeterminedthe
hand's location in the X, Y, and Z axes. Touch sensors were
integrated into the glove as well. The hand sign translation
algorithm was implemented using the C programming
language under Nios II EDS. Recognizing hand sign signals

from images can have various applications,includinghuman
control of robots and other tasks that require a simple set of
instructions. The system's functionality can be expanded by
incorporating a CMOS sensor into the setup. Overall, the
study aimed to develop a hand gesture recognition system
using FPGA technology, image processingtechniques,andan
efficient algorithm, with the potential for applications in
robotics and other fields.
In their study described in [9], Shihab Shahriar Hazari et al
focused on the recognition and translation of hand gestures,
which is a natural and expressive means of communication
for the hearing impaired. While previous research has
primarily focused on static gestures, postures, or a limited
set of dynamic gestures due to their complexity, this paper
aimed to address real-time recognition of a large set of
dynamic gestures usingthe KinectMotionSensordevice. The
challenge lies in the fact that the gesture of each user for a
particular word may vary slightly. To overcome this, the
authors employed an efficient algorithm that incorporates a
grid view approach for gesture recognition in both training
and translation modes. This algorithm enables thesystemto
effectively recognize and translate gestures. To evaluate the
performance of the proposed system, the researchers
conducted experiments involving various individuals
performing twelvedifferent words. The experimental results
demonstrated that the system achieved an approximate
success rate of 80% in accurately translating the gestures.
The use of the Kinect Motion SensorDevice,coupledwith the
efficient gesture recognition algorithm, contributes to a
more comprehensive and real-time approach to recognizing
and translating dynamic hand gestures. This research offers
promising insights into improving communication for the
hearing impaired by leveraging advanced technologies and
efficient algorithms.
In their study described in [10], Sidney Fels et al introduced
Glove-Talk-II, a system that enables the translation of hand
gestures into speech through an adaptive interface. The
system utilizes a mapping mechanism that continuously
associates hand gestures with 10 control parameters of a
parallel format speech synthesizer. This mapping allowsthe
hand to serve as an artificial vocal tract,generatingspeechin
real time. The approach offers numerous advantages,
including an extensive vocabulary, support for multiple
languages, and direct control over fundamental frequency
and volume. The latest version of Glove-Talk-II incorporates
various input devices such as a Cyber glove, a Contact Glove,
a polhemus sensor, and a foot-pedal. It also incorporates a
parallel format speech synthesizer and three neural
networks. The task of translating gestures into speech is
divided into vowel and consonant production. A gating
network is used to weigh the outputs of a vowel neural
network and a consonant neural network. The consonant
network and gating network are trained using examples
provided by the user. On the other hand, the vowel network
establishes a fixed, user-defined relationship between hand
position and vowel sounds, eliminating the need fortraining
examples. Additionally, the system employs fixed mappings
from the input devices to generate volume, fundamental
frequency, and stop consonants. The research involved one
subject who underwent approximately100hoursoftraining
to achieve intelligiblespeech usingGlove-Talk-II.Thesubject
progressed through eight distinct stages while learning to
speak, and although the speech rate was slow, the quality of
the speech exhibited more natural-soundingpitchvariations
compared to text-to-speech synthesizers. The development
of Glove-Talk-II represents a significant advancement in
translating hand gestures into speech, providing a unique
and adaptable interface for individuals to communicate
using their gestures in a more natural and expressive
manner.
3.PROPOSED WORK
3.1 OBJECTIVE
The primary objective of the smart speaking glove for
speech-impaired people using an IR sensor andpanicswitch
is to provide communication assistance and ensure the
safety of individuals in emergency situations. The glove
incorporates technology to address the specific needs of
speech-impaired individuals, providing them with an
alternative means of communication and a way to signal for
help when needed. Here is a breakdown of the main
objectives:
Communication Assistance: The smart gloveaimstoassist
speech-impaired individuals in expressing themselves by
translating their gestures or hand movements into spoken
words. The IR sensor embedded in the glove detects these
movements and converts them intoaudiblespeech,enabling
the wearer to communicate with others effectively.
Mobility and Accessibility: The glove is designed to be
wearable and portable, allowing individuals to use it
wherever they go. Its compact design ensures that the user
can carry it with ease, enhancing their mobility and
accessibility to communication.
Emergency Situations: The panicswitchintegratedintothe
glove serves as a safety feature. In case of an emergency, the
user can activate the panic switch, which triggers an alarm
or distress signal. This feature helps individuals quickly and
effectively signal for help when they are unable to
communicate verbally.
Location Tracking: The glove incorporates location-
tracking capabilities to determine the wearer's current
location. This feature enablesotherstoquicklylocateandaid
in emergency situations, further enhancing the safety of the
user.
Independence and Empowerment: By providing an
alternative communication method anda safetymechanism,

the smart speaking glove aims to promote theindependence
and empowerment of speech-impaired individuals.Itallows
users to navigate their daily lives with greater confidence
and autonomy, knowing that they have a reliable means of
communication and a safety feature at their disposal.
Overall, the objective of the smart speakinggloveistobridge
the communication gap for speech-impaired individuals,
enhance their safety in emergency situations, and enable
them to lead more independent and empowered lives.
Fig -1: Block Diagram
3.2 SYSTEM MODEL
The smart speaking glove for speech-impaired people
consists of both hardware and software components, as
depicted in Fig-1. The system is divided into three main
parts:
 Gesture input
 Processing the data
 Voice output
Gesture Input: The glove isequippedwithIR sensorsplaced
strategically on the fingers, allowing the user to make
gestures easily. These sensors detect the hand movements
and produce corresponding voltage values. Each gesture is
associated with a specific resistance value, which is
converted into a voltage signal.
Processing the Data: The voltage signals from the IR
sensors are in analog form and need to be processed. An
Arduino Nano microcontroller with an inbuilt ADC (Analog-
to-Digital Converter) is used to convert the analog signals
into digital form. The microcontroller stores predefined
gestures and their corresponding messages in a database,
which can be in different languages. The Arduino Nano
compares the input voltage with the threshold valuesstored
in the database to identify the gesture made by the user.
Voice Output: The processed data from the ArduinoNanois
sent to an APR33A3 module and an LCD display. The LCD
display shows the message associated with the recognized
gesture from the database. The APR module, also known as
an Auto Playback Recorder, generates the speech signal
corresponding to the message and plays it through a
speaker. The user has the option to select their desired
language for communication using language selection
switches. In case of emergency situations, a panic switch is
provided. When activated, it triggers a message containing
the word "EMERGENCY" along with the device user's
location, which is tracked using a GSM and GPS module. The
location information is sent to a guardian or designated
recipient in the form of Google maps.
Overall, the smart speaking glove combines hardware
components such as flexsensors,ArduinoNano,LCDdisplay,
IR sensors, and modules for voice output and location
tracking, along with software programming on the Arduino,
to enable speech-impaired individuals to communicate
effectively and seek help in emergencies.
3.2.1 ARDUINO NANO (ATMEGA 328)
The Arduino Nano isa versatileandcompactmicrocontroller
board that is based on the ATmega328P chip. It belongs to
the Arduino family of development boardsandisspecifically
designed for small-scale projectsthatrequirea cost-effective
and low-power solution. The board functions by executing
instructions stored in its flash memory and can be
programmed using the Arduino software, which utilizes a
simplified version of the C++ programming language.Power
can be supplied to the Arduino Nano either through a USB
connection or an external power source, and it
communicates with other devices through various digital
and analog input/output pins. The Arduino Nano comes
equipped with onboard components, including voltage
regulators and a USB-to-serial converter,whichcontributeto
its functionality. This board can be easily connected to other
electronic components such as sensors, actuators, and
displays, enabling users to create interactive projects and
prototypes. Due to its versatility and compact size, the
Arduino Nano is widely utilized in applications such as
robotics, homeautomation,andwearabletechnology,among
others.
3.2.2 INFRARED SENSOR
The IR transmitters emit infrared light, while the IR
receivers detect the reflected light. When the emitted light
strikes a white surface, it is reflectedtowardstheIR receiver,
causing minor voltage changes. As a result, the IR receiver
detects the presence of infrared photons. On the other hand,
when the light strikes a black surface, it is absorbed, and no
reflected light reaches the IR receiver. Consequently, the IR
receiver does not detect any infrared rays. In this project, an
Arduino is employed to process the inputfromtheIR sensor.

When the IR sensor detects a white surface, it sends a signal
of 1 (HIGH) to the Arduino. Conversely, when the sensor
detects a black line, it sends a signal of 0 (LOW) to the
Arduino. This allows the Arduino to distinguish betweenthe
white surface and the black line, enabling the robottofollow
the desired path.
3.2.3 GSM MODULE
SIMCom Wireless Solutions is a subsidiary of SIM
Technology GroupLtd.(stock code:2000.HK)andspecializes
in the development and sale of wireless modules. These
modules are designed based on various technology
platforms such as GSM/GPRS/EDGE, WCDMA/HSDPA, and
TD-SCDMA. Like a mobile phone, a GSM modem accepts a
SIM card and utilizes a mobile operator subscription.
SIMCom Wireless Solutions is a rapidly expanding wireless
company that offers a wide range of wireless modules to
meet diverse requirements. They provide specializeddesign
solutions for mobile computing, GPS, and otherapplications.
Additionally, SIMCom Wirelesscollaborateswiththird-party
entities to enhance their product offerings and provide
comprehensive solutions in the field of wireless
communication.
3.2.4 GPS MODULE
The GPS module is a satellite navigation system that
provides users with position and time data in various
weather conditions. It is widely used in ships, vehicles, and
trucks for navigation purposes. Both military and civilian
users benefit from the global capabilities of GPS, which
continuously delivers real-time, three-dimensional location,
navigation, and timing information. To integrate the GPS
module with an Arduino board, it is necessary to disconnect
the Arduino IC (Atmega chip) from the Arduino board,
leaving only the serial circuitry active. This setup is referred
to as the Gateway mode. In the serial window, sentences
starting with the "$" sign can be observed, which are in the
NMEA format. The GPS module transmits real-time tracking
position data in NMEA format, which consists of multiple
sentences.
3.2.5 APR 33A3 (AUDIO PLAYBACK RECORDER)
The APR33A3 is an integrated circuit commonly used for
voice and sound applications, providingaudiorecordingand
playback capabilities when integrated into a smart speaking
glove. Within the smart speaking glove, the APR33A3 has an
onboard analog-to-digital converter (ADC) that converts
incoming audio signals from the integrated microphoneinto
a digital format. The digital audio data is then stored in the
APR33A3's built-in non-volatile memory, the capacity of
which depends on the version of the APR33A3 chip used.
When playback is required, the APR33A3 retrieves the
stored digital audio data from its memory and converts it
back into analog audio signals using the onboard digital-to-
analog converter (DAC). These analog signals are then sent
to an audio amplifier and speaker within the glove, allowing
the user to hear the recorded audio playback. The APR33A3
is controlled by a micro-controller or a similar device via a
serial interface using specific commands. These commands
instruct the APR33A3 to perform operations such as
recording, playback, or stopping. User interaction with the
smart speaking glove's micro-controllercan beprogrammed
to trigger audio recording and playback based on user input
or predefined triggers. For example, pressing a specific
button on the glove may initiate recording, while pressing
another button may initiate audio playback. By
incorporating the APR33A3 into the smart speaking glove,
users can record and play back audio messages, enabling
voice-based communication and feedback withintheglove's
functionality.
3.2.6 SPEAKER
The speaker within a smart speaking glove functions by
converting electrical signalsintoaudiblesound wavesfor the
user to hear. Here is how it operates within the glove:
Electrical Signal: The smart speaking glove's micro-
controller or audio playback circuitrygeneratesanelectrical
audio signal, typically in the form of analog voltage
variations. This signal represents the desired soundorvoice
message to be played.
Amplification: Since the electrical audio signal is usually
weak, it needs to be amplified to a level that can effectively
drive the speaker. An audio amplifier circuit withintheglove
boosts the amplitude of the signal, making it stronger.
Speaker Cone and Magnet: The speaker unit consists of a
cone-shaped diaphragm, a voice coil (coil), and a permanent
magnet. The voice coil is connected to the base of the cone
and is surrounded by the magnet.
Magnetic Field and Coil Interaction: When the amplified
electrical audio signal flows through the voice coil, it
generates a varying magnetic field around the coil. This
varying magnetic field interacts with the fixed magnet,
causing the voice coil and cone to move back and forth
rapidly.
Sound Production: As the cone moves back and forth, it
displaces the surrounding air molecules, creating sound
waves. These sound waves propagate through the air as
pressure variations, producing audible sound that can be
heard by the user.
Audio Output: The sound waves generated by the vibrating
cone are emitted through the speaker's front face or an
opening in the glove, allowing the user to hear the audio
playback or voice messages.

The quality, volume level, and frequency response of the
speaker depend on its design, construction, and the
characteristics of the audio amplification circuitry. By
incorporating a speaker into a smart speaking glove, the
glove can provide audible feedback, play recorded audio
messages, and enable voice communication.
3.2.7 PANIC SWITCH
A panic switch incorporated withina smartspeakinggloveis
typically a physical button or sensor that, when activated,
triggers an immediate responseor emergencyaction.Hereis
a general overview of how it operates within the glove:
Button or Sensor: The panic switch is a distinct physical
button or sensor integrated into the glove. When pressed or
activated, it sends a signal indicating the user's intention to
invoke a panic or emergency.
Micro-controller Input: The panic switch is connected to
the glove's micro-controller or control circuitry. The micro-
controller continuously monitors the status of the panic
switch input to detect when it is activated.
Panic Event Detection: Upon detecting that the panic
switch has been activated, the micro-controllerrecognizesit
as a specific trigger event for a panic or emergency.
Immediate Response: Once the micro-controller detects
the activation of the panic switch, it initiates a predefined
response or action. The nature of this response can vary
depending on the purpose and programming of the smart
speaking glove.
3.2.8 LCD 16X2
An LCD 16 x 2 display functions by utilizing liquid crystalsto
manipulate light passing through them. It consists of 16
columns and 2 rows of character cells, where each cell can
display a character or symbol. To interfacethedisplaywitha
smart speaking glove, a micro-controller or similar device is
required to send commands and data to the display. The
micro-controller controls the display by issuing specific
commands to initialize it, position the cursor, and writedata
to the desired locations on the screen. Trilateration is the
mathematical principle underlying the functioning and
operation of the Global Positioning System (GPS). By
utilizing the distances to satellites, the receiver's position
can be calculated. In the case of four satellites, the fourth
satellite serves to confirm the intended position.
Additionally, tracking the location using three satellites is
possible, with each spacecraft using a fourth satellite to
validate its intended location. The Global PositioningSystem
consists of satellites, control stations, monitor stations, and
receivers. The GPS receiver gathers data from the satellites
and applies the trilateration technique to determine a user's
precise location.
4. RESULTS AND DISCUSSION
4.1 GESTURE RECOGNITION & ITS CONVERSION
The smart speaking glove designed for individuals with
speech impairments utilizes aninfrared(IR)sensortodetect
hand movements and convert them into audible speech. In
this section, we present the structure of the Results and
Discussion section of a research paper on this topic.
RESULTS: The study involved a group of 5 participantswith
speech impairments who tested the prototype of the smart
speaking glove. Each participant wasinstructedtoperforma
series of predefined hand gestures while wearing the glove,
and the IR sensor captured the corresponding movements.
Subsequently, the glove processed the collected data and
generated speech output based on the recognized gestures.
The obtained results demonstrated that the smart speaking
glove achieved a remarkable level of accuracy in detecting
and interpreting hand movements. The IR sensor
successfully captured a wide range of gestures, including
finger movements, palm orientation, and hand shapes. The
glove effectively translated these gestures into coherent
speech output, enabling the participants to communicate
efficiently. During the testing phase, the participants
expressed a high level of satisfaction with the performance
of the glove. They found the glove to be intuitive to use and
greatly appreciated its capability to convert their hand
movements into spoken words. The system's accuracy in
recognizing gesturessignificantlyimprovedtheparticipants'
ability to express themselves, reducing their reliance on
alternative communication methods.
BIT NUMBER STATE OF SENSOR
1 OFF
0 ON
In the process of analysing the results, it was observed that
when the bit number is set to 1, indicating the appropriate
direction of finger bend, contact between the LED and IR
sensor is prevented. Consequently, the specific finger
movement is not recognized. Conversely, when the bit
number is set to 0, indicating thenon-bending positionofthe
finger, contact is established between the IR sensor andLED
installed in the glove's fingers, enabling the recognition of
the finger's gesture. The output is then presentedontheLCD
display and converted into speech output based on the
combination of finger movements. The gesture pattern is
determined based on these outcomes. The results of the
study highlight the effectiveness of the smart speakingglove
in gesture recognition and conversion. The high level of
accuracy achieved by the glove in capturingandinterpreting
hand movements holds significant promise for individuals
with speech impairments. The intuitive nature of the glove's
interface and its ability to convert gestures into speech

output offer a practical and efficient means of
communication. However, further research is necessary to
explore potential improvements and expand the range of
supported gestures. The incorporation of machine learning
algorithms or advanced signal processing techniques could
enhance the system's gesture recognition capabilities.
Additionally, user feedback and long-term usability studies
should be conducted to ensure the glove's effectiveness and
user satisfaction in real-world scenarios. Overall, the results
indicate that the smart speaking glove with IR sensor
technology has the potential to significantly improve
communication for individuals with speech impairments,
providing them with a reliable and intuitive means of
expressing themselvesthroughhand gesturesconvertedinto
audible speech.
DISCUSSION: The smart speaking glove offers a promising
solution to address the communication challenges faced by
individuals with speech impairments. By utilizing an IR
sensor to capture and interpret hand movements, the glove
successfully convertsgesturesintoaudiblespeech,providing
an alternative means of communication.Thistechnology has
the potential to significantly improve the quality of life for
speech-impaired individuals by enhancing their ability to
communicate effectively and interact with others. Oneofthe
key advantages of the smart speaking glove is its
adaptability. The system can be easily customized to
recognize different hand gesturesandaccommodatevarious
languages, ensuring its applicability to a widerangeofusers.
Furthermore, the compact and portable design of the glove
makes it convenient for everyday use in different
environments. While the initial results havebeenpromising,
there are several areas that warrant further improvement
and research. Enhancing the accuracy of gesturerecognition
is crucial to minimize errors and ensure the reliability of the
system. This can be achieved through advanced algorithms
or machine learning techniques that improve the glove's
ability to interpret complex hand movements accurately.
Additionally, optimizing the glove's ergonomicsandcomfort
is important to ensure that users can wear it comfortably for
extended periods without experiencing discomfort or
fatigue. User training and adaptation to the glove's interface
are also essential factors to consider. Investigating the
learning curve and users' ease of integrating the glove into
their daily routines will provide valuable insights into the
usability and practicality of the device. In conclusion, the
smart speaking glove holds great promise as a
communication tool for individuals with speech
impairments. With further enhancements and research,
including improved gesture recognition, optimized
ergonomics, and user training, this technology has the
potential to empower speech-impairedindividuals,granting
them greater independence and facilitating meaningful
interactions with others.
4.2 EMERGENCY SITUATION INDICATOR
The inclusion of an emergency button in devices designed
for speech-impaired individuals serves as a vital feature to
ensure their safety and provide swift assistance during
emergency situations. Here is a more refined explanation of
its usage:
Immediate Assistance: In the event of an emergency
requiring immediate aid, such as a medical crisisorpersonal
safety concern, speech-impaired individualscanactivatethe
emergency button on their device. This action triggers an
alert system that promptly notifies relevant authorities or
designated emergency contacts.
Location Identification: Equipped with GPS or other
location-tracking technologies, the device determines the
precise whereabouts of the individual at the time of
emergency button activation. This crucial information is
transmitted along with the alert, enabling emergency
responders to quickly locate and reach the person in need.
Swift Response: By sharing the individual's current
location, emergency responders can rapidly assess the
situation and provide appropriateassistance.Thisexpedited
response time can significantly mitigate the impact of
emergencies and potentially save lives.
User Accessibility: The emergency button should be
thoughtfully designed with the specific needs of speech-
impaired individuals in mind. It should be easily accessible,
prominently displayed on the device, and incorporate
mechanisms to prevent accidental activation, thereby
minimizing false alarms.
Integration with SupportSystems: Seamlessintegrationof
the emergency button with existing emergency response
systems, such as emergency call centre’s or mobile
applications, ensures that alerts are promptly received by
the appropriate authorities. This integration facilitates
efficient coordination of response efforts.
Privacy and Security Considerations: Safeguarding the
privacy and security of the user's location data is of
paramount importance. The system should implement
robust encryption measures and adhere to relevant privacy
regulations to protect the individual's personal information
from unauthorized access.
By incorporating an emergency button into devices for
speech-impaired individuals, their safetyandwell-beingcan
be significantly enhanced. Prompt access to assistance,
coupled with accurate location tracking, empowers
individuals to seek help during emergencies,providingthem
with a greater sense of security and reassurance.

Fig-2: Working model of smart speaking glove using IR
sensor
Fig-3: Screenshot of Current Location
5.CONCLUSION AND FUTURE SCOPE
Conclusion: The smart speaking glove utilizinganIR sensor
for speech-impaired individuals presents a promising
assistive technology solution. Through the accurate
detection and interpretation of hand movements, the glove
successfullytranslatesgesturesintoaudiblespeech,enabling
effective communication. The results of testing and user
satisfaction indicate its potential tosignificantly enhancethe
quality of life and independence of speech- impaired
individuals. he compact and portable design of the glove,
coupled with its versatility in accommodating different
gestures and languages, makes it a practical and accessible
communication tool. The positive feedback from users
highlights its intuitive interface and its ability to reduce
reliance on other communication methods.
Future Scope: While the smart speaking glove using an IR
sensor has shown promising results, there are several
avenues for future research and development:
Gesture Recognition Improvement: Furtherrefinementof
the gesture recognition algorithms can enhance accuracy
and reliability, reducing the occurrence of errors in
translating hand movements into speech output. Advanced
machine learning techniques,suchasdeeplearning,couldbe
explored to achieve higherprecisionandexpandtherangeof
recognized gestures.
Multimodal Communication: Integration of additional
sensors, such as accelerometers or flex sensors, can capture
more nuanced hand movements and gestures, enabling a
richer and more expressive form of communication.
Incorporating other modalities, such as haptic feedback,can
enhance the user experience by providing tactile cues or
responses.
Natural Language Processing: Advancements in natural
language processing (NLP) can improve the coherence and
fluency of the speech output generated bytheglove.This can
include better sentence structure, intonation, and context-
awareness to ensure more natural and effective
communication.
Accessibility and Customization: Furthereffortsshould be
made to ensure the glove's accessibility for individuals with
varying levels of hand mobility or dexterity. Customization
options, such as adjustable sensitivity or gesture mapping,
can accommodate different user preferences and
requirements.
Long-Term Usability and Comfort: Investigating the long-
term usability and comfort of the glove is crucial. User
studies can assess factors like ergonomics,breathability, and
ease of wear to ensure extended periods of use without
causing discomfort or fatigue.
IntegrationwithSmartDevices:Exploringintegrationwith
existing smart devices, such as smartphones or tablets, can
enhance the functionality and connectivity of the smart
speaking glove. This can include features like text-to-speech
conversion, message drafting, or compatibility with
communication apps.
User Training and Support: Continued user training and
support resources are essential tofacilitatetheadoptionand
effective use of the smart speaking glove. User feedback and
engagement should be actively sought to drive ongoing
improvements and address user needs.
In conclusion, the smart speakinggloveutilizinganIRsensor
holds great promise as an assistive technology for speech-
impaired individuals. Continued research and development,
along with user-centred design principles, canfurtherrefine
its performance, expand its capabilities, and improve the
overall communication experience for speech-impaired
individuals.
REFERENCES
[1] A. Z. Shukor, M. F. Miskon, M. H. lamaluddin, F. bin
Ali@Ibrahim, M. F. Asyraf, and M. B. bin Bahar, "A new
data glove approach for Malaysian sign language

detection," IEEE International SymposiumonRobotics
and Intelligent Sensors (IRIS 2015)Procedia Computer
Science, Vol.76 , 2015.
[2] Anbarasi Rajamohan, Hemavathy R., DhanalakshmiM.,
“Deaf-Mute CommunicationInterpreter,”International
Journal of Scientific Engineering and Technology,
Volume 2 Issue 5, pp: 336-341, 1 May 2013, ISSN:
2277- 1581.
[3] Gunasekaran K., Manikandan. R., “Sign Language to
Speech Translation System UsingPICMicrocontroller”,
International Journal of Engineering and Technology
(IJET), Vol 5 No 2, pp 1024-1028, Apr-May 2013, ISSN:
0975-4024.
[4] H. Ikeda, H. Sagawa, T. Sakiyama, M. Ohki. and Y.
Kaneko,” Sign language editing apparatus," US Patent
5,990,878, v. J77-D-II, pp. 753–763, 1994.
[5] Laura Dipietro, Angelo M. Senior, member IEEE, “A
Survey of Glove Based System and their applications,”
IEEE transaction on System,Man,andCybernetics-Part
C: Application and Review, vol. 38, no. 4, 2008.
[6] M. G. Kumar, M. K. Gurjar, and M.S. Singh, "American
sign language translating glove using flex sensor,"
Imperial Journal of Interdisciplinary Research, vol. 2,
no. 6, 2016.
[7] Madhuri, Y.; Anitha, G.; Anburajan, M., “Vision-based
sign language translation device," Information
CommunicationandEmbeddedSystems(ICICES),2013
International Conference on, vol., no., pp.565,568, 21-
22 Feb. 2013, DOI: 10.1109/ICICES.2013.65083.
[8] MohdYusofRahiman WanAbdul Aziz,―Developmentof
Sign Signal Translation System BasedonAltera ‘sFPGA
DE2 Board‖, International Journal ofHumanComputer
Interaction (IJHCI), Vol. 2, Issue 3, pp. 101-114, 2011.
[9] Shihab Shahriar Hazari, Asaduzzaman, Lamia Alam,
and Nasim Al Goni wrote "Designing a sign language
translation system utilizing Kinect motion sensor
device," International Conference on Electrical,
Computer and Communication Engineering (ECCE),
February 16-18, 2017, Cox’s Bazar, Bangladesh.
[10] Sidney Fels and Geoffrey Hinton, “Glove Talk II,” IEEE
transaction on neural networks, Department of
Computer Science of University of Toronto, Toronto,
Volume 9 No 1, 6 November 1998.

GLOVE BASED GESTURE RECOGNITION USING IR SENSOR

More Related Content

Similar to GLOVE BASED GESTURE RECOGNITION USING IR SENSOR (20)

More from IRJET Journal (20)

Recently uploaded (20)

GLOVE BASED GESTURE RECOGNITION USING IR SENSOR