Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments

Sign languages are natural languages used mostly by deaf and hard of hearing people. Different development opportunities for people with these disabilities are limited because of communication problems. The advances in technology to recognize signs and gestures will make computer supported interpret...

Descripción completa

Detalles Bibliográficos
Autores: Quesada Quirós, Luis, López Herrera, Gustavo, Guerrero Blanco, Luis Alberto
Tipo de recurso: artículo
Fecha de publicación:2017
País:Costa Rica
Institución:Universidad de Costa Rica
Repositorio:Kérwá
OAI Identifier:oai:kerwa.ucr.ac.cr:10669/74423
Acceso en línea:https://link.springer.com/article/10.1007/s12652-017-0475-7
http://rdcu.be/qiDB
https://hdl.handle.net/10669/74423
Access Level:acceso abierto
Palabra clave:American sign language
Leap motion
Intel RealSense
Support vector machine
Automatic sign language recognition
Natural user interfaces
id CR_7bb25358c9ea58accb32b5fccd2d1e07
oai_identifier_str oai:kerwa.ucr.ac.cr:10669/74423
network_acronym_str CR
network_name_str Costa Rica
repository_id_str
dc.title.es_ES.fl_str_mv Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments
title Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments
spellingShingle Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments
Quesada Quirós, Luis
American sign language
Leap motion
Intel RealSense
Support vector machine
Automatic sign language recognition
Natural user interfaces
title_short Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments
title_full Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments
title_fullStr Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments
title_full_unstemmed Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments
title_sort Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments
dc.creator.none.fl_str_mv Quesada Quirós, Luis
López Herrera, Gustavo
Guerrero Blanco, Luis Alberto
author Quesada Quirós, Luis
author_facet Quesada Quirós, Luis
López Herrera, Gustavo
Guerrero Blanco, Luis Alberto
author_role author
author2 López Herrera, Gustavo
Guerrero Blanco, Luis Alberto
author2_role author
author
dc.subject.es_ES.fl_str_mv American sign language
Leap motion
Intel RealSense
Support vector machine
Automatic sign language recognition
Natural user interfaces
topic American sign language
Leap motion
Intel RealSense
Support vector machine
Automatic sign language recognition
Natural user interfaces
description Sign languages are natural languages used mostly by deaf and hard of hearing people. Different development opportunities for people with these disabilities are limited because of communication problems. The advances in technology to recognize signs and gestures will make computer supported interpretation of sign languages possible. There are more than 137 different sign languages around the world; therefore, a system that interprets them could be beneficial to all, especially to the Deaf Community. This paper presents a system based on hand tracking devices (Leap Motion and Intel RealSense), used for signs recognition. The system uses a Support Vector Machine for sign classification. Different evaluations of the system were performed with over 50 individuals; and remarkable recognition accuracy was achieved with selected signs (100% accuracy was achieved recognizing some signs). Furthermore, an exploration on the Leap Motion and the Intel RealSense potential as a hand tracking devices for sign language recognition using the American Sign Language fingerspelling alphabet was performed.
publishDate 2017
dc.date.issued.none.fl_str_mv 2017-03-22
dc.date.accessioned.none.fl_str_mv 2018-04-06T20:05:17Z
dc.date.available.none.fl_str_mv 2018-04-06T20:05:17Z
dc.type.none.fl_str_mv artículo original
http://purl.org/coar/resource_type/c_2df8fbb1
info:eu-repo/semantics/article
format article
dc.identifier.citation.none.fl_str_mv https://link.springer.com/article/10.1007/s12652-017-0475-7
http://rdcu.be/qiDB
dc.identifier.issn.none.fl_str_mv 1868-5137
1868-5145
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/10669/74423
dc.identifier.doi.none.fl_str_mv 10.1007/s12652-017-0475-7
dc.identifier.codproyecto.none.fl_str_mv 320-B5-291
url https://link.springer.com/article/10.1007/s12652-017-0475-7
http://rdcu.be/qiDB
https://hdl.handle.net/10669/74423
identifier_str_mv 1868-5137
1868-5145
10.1007/s12652-017-0475-7
320-B5-291
dc.language.iso.es_ES.fl_str_mv en_US
language_invalid_str_mv en_US
dc.rights.none.fl_str_mv acceso abierto
http://purl.org/coar/access_right/c_abf2
info:eu-repo/semantics/openAccess
rights_invalid_str_mv acceso abierto
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.source.es_ES.fl_str_mv Journal of Ambient Intelligence and Humanized Computing, Vol. 8(4), pp 625–635
dc.source.none.fl_str_mv reponame:Kérwá
instname:Universidad de Costa Rica
instacron:UCR
instname_str Universidad de Costa Rica
instacron_str UCR
institution UCR
reponame_str Kérwá
collection Kérwá
bitstream.url.fl_str_mv https://www.kerwa.ucr.ac.cr/bitstreams/85b0d42c-7b63-406f-8ee6-86d9be7033c8/download
https://www.kerwa.ucr.ac.cr/bitstreams/25ccc7d8-bb4b-4e25-b340-8ab411c756bd/download
https://www.kerwa.ucr.ac.cr/bitstreams/f50dcddc-1d55-48fd-801f-8a013ca1e18e/download
https://www.kerwa.ucr.ac.cr/bitstreams/011a943f-991b-4455-a773-36f498a4aa81/download
bitstream.checksum.fl_str_mv bd84792c9349cf60721fb58f8309d3fa
f390d89ef134b2cf93d74a0f1594d4ae
1277551efc45c5e59ada90b188ac23ff
ecf71c80f139389961ecc4fa5b8c19e0
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Kérwá - Universidad de Costa Rica
repository.mail.fl_str_mv meilyn.garro@ucr.ac.cr
_version_ 1849325636797071360
spelling Quesada Quirós, Luis8e3f2ae4-2a80-4ba6-b9c1-02a3fa89836a600López Herrera, Gustavo389cc6a9-7caf-4549-b393-3098a0d367c5600Guerrero Blanco, Luis Albertoac632404-133b-48f0-b394-f965271375216002018-04-06T20:05:17Z2018-04-06T20:05:17Z2017-03-22https://link.springer.com/article/10.1007/s12652-017-0475-7http://rdcu.be/qiDB1868-51371868-5145https://hdl.handle.net/10669/7442310.1007/s12652-017-0475-7320-B5-291Sign languages are natural languages used mostly by deaf and hard of hearing people. Different development opportunities for people with these disabilities are limited because of communication problems. The advances in technology to recognize signs and gestures will make computer supported interpretation of sign languages possible. There are more than 137 different sign languages around the world; therefore, a system that interprets them could be beneficial to all, especially to the Deaf Community. This paper presents a system based on hand tracking devices (Leap Motion and Intel RealSense), used for signs recognition. The system uses a Support Vector Machine for sign classification. Different evaluations of the system were performed with over 50 individuals; and remarkable recognition accuracy was achieved with selected signs (100% accuracy was achieved recognizing some signs). Furthermore, an exploration on the Leap Motion and the Intel RealSense potential as a hand tracking devices for sign language recognition using the American Sign Language fingerspelling alphabet was performed.Universidad de Costa Rica/[320-B5-291]/UCR/Costa RicaMinisterio de Ciencia, Tecnología y Telecomunicaciones//MICITT/Costa RicaConsejo Nacional para Investigaciones Científicas y Tecnológicas//CONICIT/Costa RicaUCR::Vicerrectoría de Investigación::Unidades de Investigación::Ingeniería::Centro de Investigaciones en Tecnologías de Información y Comunicación (CITIC)UCR::Vicerrectoría de Docencia::Ingeniería::Facultad de Ingeniería::Escuela de Ciencias de la Computación e Informáticaen_USacceso abiertohttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessJournal of Ambient Intelligence and Humanized Computing, Vol. 8(4), pp 625–635reponame:Kérwáinstname:Universidad de Costa Ricainstacron:UCRAmerican sign languageLeap motionIntel RealSenseSupport vector machineAutomatic sign language recognitionNatural user interfacesAutomatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairmentsartículo originalhttp://purl.org/coar/resource_type/c_2df8fbb1info:eu-repo/semantics/articleORIGINALs12652-017-0475-7.pdfs12652-017-0475-7.pdfapplication/pdf1106362https://www.kerwa.ucr.ac.cr/bitstreams/85b0d42c-7b63-406f-8ee6-86d9be7033c8/downloadbd84792c9349cf60721fb58f8309d3faMD51LICENSElicense.txtlicense.txttext/plain; charset=utf-82437https://www.kerwa.ucr.ac.cr/bitstreams/25ccc7d8-bb4b-4e25-b340-8ab411c756bd/downloadf390d89ef134b2cf93d74a0f1594d4aeMD52TEXTs12652-017-0475-7.pdf.txts12652-017-0475-7.pdf.txtExtracted texttext/plain47601https://www.kerwa.ucr.ac.cr/bitstreams/f50dcddc-1d55-48fd-801f-8a013ca1e18e/download1277551efc45c5e59ada90b188ac23ffMD53THUMBNAILs12652-017-0475-7.pdf.jpgs12652-017-0475-7.pdf.jpgGenerated Thumbnailimage/jpeg5226https://www.kerwa.ucr.ac.cr/bitstreams/011a943f-991b-4455-a773-36f498a4aa81/downloadecf71c80f139389961ecc4fa5b8c19e0MD5410669/744232024-06-03 18:06:12.482embargo2150-03-01oai:kerwa.ucr.ac.cr:10669/74423https://www.kerwa.ucr.ac.crInstitucionalhttp://www.kerwa.ucr.ac.crUniversidadhttp://www.ucr.ac.crhttps://kerwa.ucr.ac.cr/oai/requestmeilyn.garro@ucr.ac.crCosta RicaNo aplicaNo aplicaNo aplicaopendoar:18712025-03-29T18:09:55.704Kérwá - Universidad de Costa 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
score 15.228081

Similares en LA Referencia