Melola Discovery

← Melola Discovery

Journal

Sign Language Detection Application to Facilitate Communication for Speech and Hearing Impaired Individuals Based on Computer Vision Technology Using Inception Resnetv2

Rekayasa · Vol. 20 No. 2 (2022) · pp. 108–117

DOI
10.15294/rekayasa.v20i2.19433
ISSN
2527-6964, 0216-6631
Published
2022-12-31
Publisher
Universitas Negeri Semarang
Language
eng

Abstract

Communication is a fundamental human need, yet not everyone possesses perfect communication abilities. People Communication is a fundamental human need, yet individuals with speech and hearing impairments face challenges due to the limited understanding of sign language among the general public. This study applies Artificial Intelligence and Computer Vision to enhance communication accessibility by detecting hand gestures and converting them into text. The lack of real-time sign language translation remains a barrier for individuals with disabilities. Existing systems often struggle with accuracy and device compatibility. This research develops and evaluates HARDISC, an Android-based application that recognizes letters A–Z through hand movement detection using a camera. The goal is to provide an effective and inclusive communication tool for the speech and hearing impaired. HARDISC utilizes Transfer Learning with Inception ResNetV2 and VGG16 for gesture classification. Image processing enables the camera to detect and translate hand movements into text. Model evaluation was based on accuracy, loss values, and device compatibility. Results show Inception ResNetV2 achieved 98.98% accuracy with a 0.0417 loss value, while VGG16 recorded 99.40% accuracy with a 0.0146 loss value, demonstrating high performance. HARDISC is compatible with Android KitKat 4 to Android 12, ensuring accessibility. This application provides an innovative, real-time solution to bridge communication gaps for individuals with speech and hearing impairments, improving their interaction with the general public.

Keywords

Collaboration network of the authors

25 authors · 62 co-authorship links

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Diponegoro University
  • State University of Semarang
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Riana DM PutriAffiliation unknown1
Isdiyarto IsdiyartoAffiliation unknown1
Azizah MunawarohAffiliation unknown1
Niko Dwi CahyoAffiliation unknown1
Riana Defi Mahadji PutriState University of Semarang1
Rini Kartiko SariAffiliation unknown1
Eko SupraptonoAffiliation unknown1
Galang Wahid KurniawanAffiliation unknown1
Mohamad IrfanAffiliation unknown1
Sonhaji SonhajiAffiliation unknown1
Ardhana Luthfi HidayattullahAffiliation unknown1
Catur Rini WidyastutiAffiliation unknown1
Radenrara Dewi Artanti PutriAffiliation unknown1
Delvani Putri Faradilla HamidiAffiliation unknown1
MohammadAffiliation unknown1
Dwi Kharisma LuthfianiAffiliation unknown1
Ade Rahmania YuningsihAffiliation unknown1
Rahmat GernowoDiponegoro University1
R. Rizal IsnantoDiponegoro University1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journal.unnes.ac.id/journals/rekayasa/oai, first harvested 6 Nov 2026, last seen 8 Nov 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Sign Language Detection Application to Facilitate Communication for Speech and Hearing Impaired Individuals Based on Computer Vision Technology Using Inception Resnetv2</dc:title>
	<dc:creator xml:lang="en">Arfriandi, Arief</dc:creator>
	<dc:creator xml:lang="en">Prabowo, Yoga Agung</dc:creator>
	<dc:creator xml:lang="en">Najuda, Moh Dafi</dc:creator>
	<dc:creator xml:lang="en">Puspita, Tri Anggi Ratna</dc:creator>
	<dc:creator xml:lang="en">Virnanda, Shakira Wahyu</dc:creator>
	<dc:creator xml:lang="en">Sunardiyo, Said</dc:creator>
	<dc:subject xml:lang="en">Artificial Intelligence </dc:subject>
	<dc:subject xml:lang="en">Computer Vision</dc:subject>
	<dc:subject xml:lang="en">Disabilities </dc:subject>
	<dc:subject xml:lang="en">HARDISC</dc:subject>
	<dc:subject xml:lang="en">real-time</dc:subject>
	<dc:description xml:lang="en">Communication is a fundamental human need, yet not everyone possesses perfect communication abilities. People Communication is a fundamental human need, yet individuals with speech and hearing impairments face challenges due to the limited understanding of sign language among the general public. This study applies Artificial Intelligence and Computer Vision to enhance communication accessibility by detecting hand gestures and converting them into text. The lack of real-time sign language translation remains a barrier for individuals with disabilities. Existing systems often struggle with accuracy and device compatibility. This research develops and evaluates HARDISC, an Android-based application that recognizes letters A–Z through hand movement detection using a camera. The goal is to provide an effective and inclusive communication tool for the speech and hearing impaired. HARDISC utilizes Transfer Learning with Inception ResNetV2 and VGG16 for gesture classification. Image processing enables the camera to detect and translate hand movements into text. Model evaluation was based on accuracy, loss values, and device compatibility. Results show Inception ResNetV2 achieved 98.98% accuracy with a 0.0417 loss value, while VGG16 recorded 99.40% accuracy with a 0.0146 loss value, demonstrating high performance. HARDISC is compatible with Android KitKat 4 to Android 12, ensuring accessibility. This application provides an innovative, real-time solution to bridge communication gaps for individuals with speech and hearing impairments, improving their interaction with the general public.</dc:description>
	<dc:publisher xml:lang="en">Universitas Negeri Semarang</dc:publisher>
	<dc:date>2022-12-31</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unnes.ac.id/journals/rekayasa/article/view/19433</dc:identifier>
	<dc:identifier>10.15294/rekayasa.v20i2.19433</dc:identifier>
	<dc:source xml:lang="en">Rekayasa; Vol. 20 No. 2 (2022); 108-117</dc:source>
	<dc:source>2527-6964</dc:source>
	<dc:source>0216-6631</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.unnes.ac.id/journals/rekayasa/article/view/19433/3338</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2022 Rekayasa : Jurnal Penerapan Teknologi dan Pembelajaran</dc:rights>
</oai_dc:dc>