Hand Gesture Recognition For Deaf and Blind People

Volume 7, Issue 4, April – 2022 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
Hand Gesture Recognition for Deaf and Blind People

Pakshal Jain, Chetan Kumarkar, Monali Bambode, Pradnya Kad, Prof. Pradnya Tapkir-Kad
Department of Computer Engineering,
Dr. D. Y Patil Institute of Technology, Pimpri, Pune
Abstract:- Sign language is a unique type of medium through various way. These individuals use signs to
communication language which is essential for bridging impart and offer their viewpoints. Hand motions are the
the commuication gap between deaf and dumb people. implicit traded considerations and these signals are
In each sign language, there are various signs with perceived with vision. This nonverbal correspondence of
variations in palm size, shape and motion and placement hard of hearing and visually impaired individuals is called
of hand which plays a major in each sign. A large communication via gestures. The hand motion is a
number of applications have been put forward by nonverbal approach to imparting. It contains semantic
various researchers. In the past few years, in these substance that conveys a tremendous measure of data in
applications many remarkable changes have been made communication through signing. Thus, programmed hand
using deep learning concepts. Throughout this survey, signal acknowledgment is in incredible interest. Since the
we analysed these applications of hand gesture finish of twentieth century, this region has drawn in the
recognition using deep learning concepts from the last consideration of numerous scientists. The meaning of
few years. Although there were many notable programmed hand signal acknowledgment has expanded
improvements in the accuracy in hand gesture due to underneath reasons [1]: (1) the developing pace of the
recognition, there are still many complications that almost totally senseless populace, and (2) the utilization of
needs to be resolved. We put forward a taxonomy to vision-based and touchless gadgets like computer games,
clasify the proposed apllications for future lines of savvy TV control, and augmented reality applications. In
research in the field. Our objective is to develop an our undertaking, our fundamental spotlight is on making a
application that can recognize hand gestures and signs. model which will actually want to perceive hand motion to
We will train that model in a way that sign language will shape a total sentence by incorporating each signal. Gesture
be converted into text and audio. This will help people based communication acknowledgment would assist with
communicate with people who are deaf and blind. The connecting correspondence hole between the clients in the
application will recognize hand gestures by comparing public arena. While correspondence innovations and devices
the input with pre-existing datasets formed using the like Skype and WhatsApp turned into an essential piece of
American sign Language. Here the input will be in the our lives, hard of hearing individuals have numerous
form of a real-time video of hand signals of sign troubles for utilizing these advances. Day to day
language. We will convert those signs into text as well as correspondence of the hard of hearing local area with the
audio as output for users to recognize the signs which significant hearing local area are effectively open utilizing
are captured by camera and presented by the sign these advancements. Subsequently, gesture based
language speaker. communication, as a primary kind of the hand signals
including visual movements and signs, is utilized as a
Problem Statement: Conversion of sign language using correspondence framework to help the hard of hearing and
hand gestures into text and audio for deaf and blind people. visually impaired local area for everyday correspondence.
language includes the use of various pieces of the body,
Keyword:- Hand Gestures, Sign Language, Communication, similar to fingers, hand and arm. There are four principle
Convolutional Neural Network(CNN). boundaries in marking, which are hand-shape, palm
I. INTRODUCTION direction development and area. To claim an exact sign
word, those four boundaries should be performed
American gesture based communication is the most accurately.The present work in language acknowledgment
utilized communication through signing. The main issue utilize prior dataset including pictures of only one letters in
hard of hearing individuals face is correspondence hole order. We might want to foster an application that might be
between them. Therfore the answer for them is to connect applied during a discussion among hard of hearing and
the correspondence hole utilizing hand signal visually impaired individuals. To do this, the proposed
acknowledgment. Thoghts like discourse, signs and visuals application should be productive and savvy to the point of
can be traded during the time spent correspondence. To isolating the info pictures, including a few characters,
communicate their thoughts, hard of hearing individuals words, or sentences, into independent characters, words, or
utilizes different hand motions. Correspondence is the sentences and convert the message into sound as well as the
giving of data by talking, composing or utilizing another other way around.
IJISRT22APR078 www.ijisrt.com 167

ISSN No:-2456-2165
Fig. 1: American Sign Language
II. LITERATURE SURVEY rate in removing barriers which are faced by deaf
people. By solving this problem there won’t be any
 “Sign Language Recognition: A Deep Survey” by Razieh communication gap left between deaf people and
Rastgo, Kourosh Kiania, Sergio Escalera normal people.
Deaf people use sign language for communication. In
this world, there are different types of sign languages.  “Sign Language Recognition Using Neural Network” by
And American Sign Language is one of them. We Shailesh Bachani, Shubham Dixit,Rohin Chadha,Prof.
created a model which will be helpful for deaf people. Avinash Bagul
This model will translate the signs to simple sentences. Sign Language is used for communication purposes.
Sign Language contains some hand movements which
 “Hand Gesture Recognition for Sign Language Using is helpful for a person to communicate without
3DCNN” by Muneer Al-Hammadi, Ghulam Muhammad , speaking a word.This language is very popular among
Wadood Abdul, Mansour Al-Sulaima deaf people but other people avoid learning this
In this research paper, communication problems of language. Therefore, it creates a problem of
deaf people are highlighted. In this paper, sign communication and therefore it kind of creates
language information which includes human hands isolation of physically impaired people.
have been analyzed.
 “Indian Sign Language Based Static Hand Gesture
 “Dynamic Sign Language Recognition Based on Video Recognition Using Deep Learning” by SGnanapriya , Dr.
Sequence With BLSTM-3D Residual Networks” by K.Rahimunnisa, AKarthika, MGokulnath, K Logeshkumar
Yanqiu Liao, Pengwen Xiong, Weidong MIN, Weiqiong As sign language is the main language of deaf and
MIN,Jiahao LU1 dumb people. So it is difficult for a normal person to
In this paper, sign language learning using 2-D image talk with them as normal people don't understand their
sampling has been proposed. This will help to solve the language. So a framework for recognizing Sign
problem of communication of deaf people. This model Language has been introduced.
will train data and concatenate the data with the model
for better results.  “A New Benchmark on American Sign Language
Recognition using Convolutional Neural Network”
 “Machine Learning based Hand Sign Recognition” by Complicated hand movements along with their
Ms. Greeshma Pala, Ms. Jagruti Bhagwan Jethwani, Mr. constantly changing shapes and positions is observed
Satish Shivaji Kumbhar, Ms. Shruti Dilip Patil to be a difficult problem now-a-days. Problems like
Translation systems which are automatic are very these will be solved by CNN(Convolutional Neural
useful in today’s world which shows the increasing Network).

ISSN No:-2456-2165
III. PROPOSED SYSTEM APPROACH is captured by camera , it will match with the dataset which
has been created and it is stored in the specified folder. The
The system which is created to convert the hand data which is stored in these folders will serve as the input
gesture videos into simple words and also it will be able to to the Sign Language Generation.
create a sentence. Users will get expected results by using
CNN(Convolutional Neural Network). When a hand gesture
Fig. 2: Architecture
IV. CONVOLUTIONAL NEURAL NETWORK(CNN) V. CONCLUSION

ALGORITHM
The communication via gestures acknowledgment
In the architecture of Convolutional Neural framework is possible for hard of hearing individuals since
Network(CNN) takes input as 2-D structured images (or they can convey effectively through this framework. The
other input as speech signal). This is achieved by some kind framework can catch hand signals and explore the words as
of connection followed by some kind of pooling which in message design it will be helpful so that hard of hearing
results in creating various features. One of the most individuals could see these words and get the sentences.It is
important advantages of Convolutional Neural Network likewise usable for blind individuals since they need to
(CNN) is that it is easier to train and they have very less speak with typical individuals (utilizing discourse
parameters than other networks with similar rate of hidden acknowledgment).
units.
Input: Hand gestures through camera
Output: Recognize the input hand gestures and then

make a full sentence. And the play feature will read that
sentence out loud.

ISSN No:-2456-2165
REFERENCES
[1.] Razieh Rastgo, Kourosh Kiania, Sergio Escalera, “Sign

Language Recognition: A Deep Survey” (July-2020)
[2.] Muneer Al-Hammadi, Ghulam Muhammad ,Wadood
Abdul, Mansour Al-Sulaima, “Hand Gesture
Recognition for Sign Language Using 3DCNN”
(April-2020)
[3.] Yanqiu Liao, Pengwen Xiong, Weidong MIN,
Weiqiong MIN,Jiahao LU1,“Dynamic Sign Language
Recognition Based on Video Sequence With BLSTM-
3D Residual Networks” (March-2019)
[4.] Ms. Greeshma Pala, Ms. Jagruti Bhagwan Jethwani,
Mr. Satish Shivaji Kumbhar, Ms. Shruti Dilip Patil,
“Machine Learning-based Hand Sign Recognition”
(June-2021)
[5.] Shailesh bachani, Shubham dixit, Rohin chadha, Prof.
Avinash Bagul,“Sign Language Recognition Using
Neural Network” (April-2020)
[6.] SGnanapriya , Dr. K. Rahimunnisa, A Karthika, M
Gokulnath, K Logeshkumar, “Indian Sign Language
Based Static Hand Gesture Recognition Using Deep
Learning” (June-2020)
[7.] Md. Moklesur Rahman, Md. Shafiqul Islamy, Md.
Hafizur Rahmanz, Roberto Sassix, Massimo W.
Rivolta and Md Aktaruzzaman, “A New Benchmark
on American Sign Language Recognition using
Convolutional Neural Network” (May-2020)
[8.] Sakshi Sharma, Sukhwinder Singh, “Vision-based sign
recognition system: A Comprehensive Review” (June-
2020)
[9.] Deaf Cambridge Dictionary(2018). Retrieved from
Cambridge Dictionary:
https://dictionary.cambridge.org/dictionary/engl
ish/deaf
[10.] Jaoa Carriera, A. Z. (2018). Quo Vadis, Action
Recognition? A New Model and the Kinetics Dataset.
Computer Vision and Pattern

Hand Gesture Recognition For Deaf and Blind People

Uploaded by

Copyright:

Available Formats

Hand Gesture Recognition For Deaf and Blind People

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Hand Gesture Recognition For Deaf and Blind People

Uploaded by

Copyright:

Available Formats

Volume 7, Issue 4, April – 2022 International Journal of Innovative Science and Research Technology

Hand Gesture Recognition for Deaf and Blind People

IJISRT22APR078 www.ijisrt.com 167

Fig. 1: American Sign Language

IJISRT22APR078 www.ijisrt.com 168

IV. CONVOLUTIONAL NEURAL NETWORK(CNN) V. CONCLUSION

Input: Hand gestures through camera

Output: Recognize the input hand gestures and then

IJISRT22APR078 www.ijisrt.com 169

[1.] Razieh Rastgo, Kourosh Kiania, Sergio Escalera, “Sign

IJISRT22APR078 www.ijisrt.com 170

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.