Sign Language Prediction Model using Convolution Neural Network.

The barrier between the hearing and the deaf communities in Kenya is a major challenge leading to a major gap in the communication sector where the deaf community is left out leading to inequality. The study used primary and secondary data sources to obtain information about this problem, which incl...

Full description

Saved in:
Bibliographic Details
Main Authors: Rebeccah Ndungi, Samuel Karuga
Format: Article
Language:English
Published: State Islamic University Sunan Kalijaga 2022-02-01
Series:IJID (International Journal on Informatics for Development)
Subjects:
Online Access:https://ejournal.uin-suka.ac.id/saintek/ijid/article/view/3284
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849700922427441152
author Rebeccah Ndungi
Samuel Karuga
author_facet Rebeccah Ndungi
Samuel Karuga
author_sort Rebeccah Ndungi
collection DOAJ
description The barrier between the hearing and the deaf communities in Kenya is a major challenge leading to a major gap in the communication sector where the deaf community is left out leading to inequality. The study used primary and secondary data sources to obtain information about this problem, which included online books, articles, conference materials, research reports, and journals on sign language and hand gesture recognition systems. To tackle the problem, CNN was used. Naturally captured hand gesture images were converted into grayscale and used to train a classification model that is able to identify the English alphabets from A-Z.  Then identified letters are used to construct sentences. This will be the first step into breaking the communication barrier and the inequality.  A sign language recognition model will assist in bridging the exchange of information between the deaf and hearing people in Kenya. The model was trained and tested on various matrices where we achieved an accuracy score of a 99% value when run on epoch of 10, the log loss metric returning a value of 0 meaning that it predicts the actual hand gesture images. The AUC and ROC curves achieved a 0.99 value which is excellent.
format Article
id doaj-art-04c0a76f4a8b49c399b1e5fd535bbb10
institution DOAJ
issn 2252-7834
2549-7448
language English
publishDate 2022-02-01
publisher State Islamic University Sunan Kalijaga
record_format Article
series IJID (International Journal on Informatics for Development)
spelling doaj-art-04c0a76f4a8b49c399b1e5fd535bbb102025-08-20T03:18:06ZengState Islamic University Sunan KalijagaIJID (International Journal on Informatics for Development)2252-78342549-74482022-02-011029210110.14421/ijid.2021.32842909Sign Language Prediction Model using Convolution Neural Network.Rebeccah Ndungi0Samuel Karuga1Samasource KenyaComputer Science Department St Paul's University Private bag, limuru - 00217, Kenya The barrier between the hearing and the deaf communities in Kenya is a major challenge leading to a major gap in the communication sector where the deaf community is left out leading to inequality. The study used primary and secondary data sources to obtain information about this problem, which included online books, articles, conference materials, research reports, and journals on sign language and hand gesture recognition systems. To tackle the problem, CNN was used. Naturally captured hand gesture images were converted into grayscale and used to train a classification model that is able to identify the English alphabets from A-Z.  Then identified letters are used to construct sentences. This will be the first step into breaking the communication barrier and the inequality.  A sign language recognition model will assist in bridging the exchange of information between the deaf and hearing people in Kenya. The model was trained and tested on various matrices where we achieved an accuracy score of a 99% value when run on epoch of 10, the log loss metric returning a value of 0 meaning that it predicts the actual hand gesture images. The AUC and ROC curves achieved a 0.99 value which is excellent.https://ejournal.uin-suka.ac.id/saintek/ijid/article/view/3284classificationkenyan sign languagedeaf communitieshand gesturescommunication gap
spellingShingle Rebeccah Ndungi
Samuel Karuga
Sign Language Prediction Model using Convolution Neural Network.
IJID (International Journal on Informatics for Development)
classification
kenyan sign language
deaf communities
hand gestures
communication gap
title Sign Language Prediction Model using Convolution Neural Network.
title_full Sign Language Prediction Model using Convolution Neural Network.
title_fullStr Sign Language Prediction Model using Convolution Neural Network.
title_full_unstemmed Sign Language Prediction Model using Convolution Neural Network.
title_short Sign Language Prediction Model using Convolution Neural Network.
title_sort sign language prediction model using convolution neural network
topic classification
kenyan sign language
deaf communities
hand gestures
communication gap
url https://ejournal.uin-suka.ac.id/saintek/ijid/article/view/3284
work_keys_str_mv AT rebeccahndungi signlanguagepredictionmodelusingconvolutionneuralnetwork
AT samuelkaruga signlanguagepredictionmodelusingconvolutionneuralnetwork