Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent Mode

In this paper we propose a glove-based Arabic sign language recognition system using a novel technique for sequential data classification. We compile a sensor-based dataset of 40 sentences using an 80-word lexicon. In the dataset, hand movements are captured using two DG5-VHand data gloves. Data lab...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Tubaiz, Noor Ali (author)
مؤلفون آخرون: Shanableh, Tamer (author), Assaleh, Khaled (author)
التنسيق: article
منشور في: 2015
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/11073/8820
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513438467751936
author Tubaiz, Noor Ali
author2 Shanableh, Tamer
Assaleh, Khaled
author2_role author
author
author_facet Tubaiz, Noor Ali
Shanableh, Tamer
Assaleh, Khaled
author_role author
dc.creator.none.fl_str_mv Tubaiz, Noor Ali
Shanableh, Tamer
Assaleh, Khaled
dc.date.none.fl_str_mv 2015
2017-05-01T06:40:25Z
2017-05-01T06:40:25Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Tubaiz, N., Shanableh, T., & Assaleh, K. (2015). Glove-Based continuous Arabic sign language recognition in user-dependent mode. IEEE Transactions on Human-Machine Systems, 45(4), 526-533. doi:10.1109/THMS.2015.2406692
2168-2291
http://hdl.handle.net/11073/8820
10.1109/THMS.2015.2406692
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv IEEE
dc.relation.none.fl_str_mv http://doi.org/10.1109/THMS.2015.2406692
dc.subject.none.fl_str_mv Sign language recognition
Sensor gloves
Feature extraction
Pattern recognition
dc.title.none.fl_str_mv Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent Mode
dc.type.none.fl_str_mv Postprint
Peer-Reviewed
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description In this paper we propose a glove-based Arabic sign language recognition system using a novel technique for sequential data classification. We compile a sensor-based dataset of 40 sentences using an 80-word lexicon. In the dataset, hand movements are captured using two DG5-VHand data gloves. Data labeling is performed using a camera to synchronize hand movements with their corresponding sign language words. Low-complexity preprocessing and feature extraction techniques are applied to capture and emphasize the temporal dependency of the data. Subsequently, a Modified k-Nearest Neighbor (MKNN) approach is used for classification. The proposed MKNN makes use of the context of feature vectors for the purpose of accurate classification. The proposed solution achieved a sentence recognition rate of 98.9%. The results are compared against an existing vision-based approach that uses the same set of sentences. The proposed solution is superior in terms of classification rates whilst eliminating restrictions of vision-based systems.
format article
id aus_ed4ebf83f1e051a3491c3ea77019e640
identifier_str_mv Tubaiz, N., Shanableh, T., & Assaleh, K. (2015). Glove-Based continuous Arabic sign language recognition in user-dependent mode. IEEE Transactions on Human-Machine Systems, 45(4), 526-533. doi:10.1109/THMS.2015.2406692
2168-2291
10.1109/THMS.2015.2406692
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/8820
publishDate 2015
publisher.none.fl_str_mv IEEE
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent ModeTubaiz, Noor AliShanableh, TamerAssaleh, KhaledSign language recognitionSensor glovesFeature extractionPattern recognitionIn this paper we propose a glove-based Arabic sign language recognition system using a novel technique for sequential data classification. We compile a sensor-based dataset of 40 sentences using an 80-word lexicon. In the dataset, hand movements are captured using two DG5-VHand data gloves. Data labeling is performed using a camera to synchronize hand movements with their corresponding sign language words. Low-complexity preprocessing and feature extraction techniques are applied to capture and emphasize the temporal dependency of the data. Subsequently, a Modified k-Nearest Neighbor (MKNN) approach is used for classification. The proposed MKNN makes use of the context of feature vectors for the purpose of accurate classification. The proposed solution achieved a sentence recognition rate of 98.9%. The results are compared against an existing vision-based approach that uses the same set of sentences. The proposed solution is superior in terms of classification rates whilst eliminating restrictions of vision-based systems.IEEE2017-05-01T06:40:25Z2017-05-01T06:40:25Z2015PostprintPeer-Reviewedinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfTubaiz, N., Shanableh, T., & Assaleh, K. (2015). Glove-Based continuous Arabic sign language recognition in user-dependent mode. IEEE Transactions on Human-Machine Systems, 45(4), 526-533. doi:10.1109/THMS.2015.24066922168-2291http://hdl.handle.net/11073/882010.1109/THMS.2015.2406692en_UShttp://doi.org/10.1109/THMS.2015.2406692oai:repository.aus.edu:11073/88202024-08-22T12:08:23Z
spellingShingle Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent Mode
Tubaiz, Noor Ali
Sign language recognition
Sensor gloves
Feature extraction
Pattern recognition
status_str publishedVersion
title Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent Mode
title_full Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent Mode
title_fullStr Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent Mode
title_full_unstemmed Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent Mode
title_short Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent Mode
title_sort Glove-Based Continuous Arabic Sign Language Recognition in User-Dependent Mode
topic Sign language recognition
Sensor gloves
Feature extraction
Pattern recognition
url http://hdl.handle.net/11073/8820