Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language

This paper presents various spatio-temporal feature-extraction techniques with applications to online and offline recognitions of isolated Arabic Sign Language gestures. The temporal features of a video-based gesture are extracted through forward, backward, and bidirectional predictions. The predict...

Full description

Saved in:
Bibliographic Details
Main Author: Shanableh, Tamer (author)
Other Authors: Assaleh, Khaled (author), Al-Rousan, Mohammad (author)
Format: article
Published: 2007
Subjects:
Online Access:http://hdl.handle.net/11073/21363
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513441173078016
author Shanableh, Tamer
author2 Assaleh, Khaled
Al-Rousan, Mohammad
author2_role author
author
author_facet Shanableh, Tamer
Assaleh, Khaled
Al-Rousan, Mohammad
author_role author
dc.creator.none.fl_str_mv Shanableh, Tamer
Assaleh, Khaled
Al-Rousan, Mohammad
dc.date.none.fl_str_mv 2007
2021-03-14T09:59:05Z
2021-03-14T09:59:05Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv T. Shanableh, K. Assaleh and M. Al-Rousan, "Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language," in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 37, no. 3, pp. 641-650, June 2007, doi: 10.1109/TSMCB.2006.889630.
1941-0492
http://hdl.handle.net/11073/21363
10.1109/TSMCB.2006.889630
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv IEEE
dc.relation.none.fl_str_mv https://doi.org/10.1109/TSMCB.2006.889630
dc.subject.none.fl_str_mv Feature extraction
Motion analysis
Pattern classification
Visual languages
dc.title.none.fl_str_mv Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language
dc.type.none.fl_str_mv Peer-Reviewed
Postprint
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description This paper presents various spatio-temporal feature-extraction techniques with applications to online and offline recognitions of isolated Arabic Sign Language gestures. The temporal features of a video-based gesture are extracted through forward, backward, and bidirectional predictions. The prediction errors are thresholded and accumulated into one image that represents the motion of the sequence. The motion representation is then followed by spatial-domain feature extractions. As such, the temporal dependencies are eliminated and the whole video sequence is represented by a few coefficients. The linear separability of the extracted features is assessed, and its suitability for both parametric and nonparametric classification techniques is elaborated upon. The proposed feature-extraction scheme was complemented by simple classification techniques, namely, K nearest neighbor (KNN) and Bayesian, i.e., likelihood ratio, classifiers. Experimental results showed classification performance ranging from 97% to 100% recognition rates. To validate our proposed technique, we have conducted a series of experiments using the classical way of classifying data with temporal dependencies, namely, hidden Markov models (HMMs). Experimental results revealed that the proposed feature-extraction scheme combined with simple KNN or Bayesian classification yields comparable results to the classical HMM-based scheme. Moreover, since the proposed scheme compresses the motion information of an image sequence into a single image, it allows for using simple classification techniques where the temporal dimension is eliminated. This is actually advantageous for both computational and storage requirements of the classifier.
format article
id aus_db153616fef632909d006f7dfe0488a6
identifier_str_mv T. Shanableh, K. Assaleh and M. Al-Rousan, "Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language," in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 37, no. 3, pp. 641-650, June 2007, doi: 10.1109/TSMCB.2006.889630.
1941-0492
10.1109/TSMCB.2006.889630
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/21363
publishDate 2007
publisher.none.fl_str_mv IEEE
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign LanguageShanableh, TamerAssaleh, KhaledAl-Rousan, MohammadFeature extractionMotion analysisPattern classificationVisual languagesThis paper presents various spatio-temporal feature-extraction techniques with applications to online and offline recognitions of isolated Arabic Sign Language gestures. The temporal features of a video-based gesture are extracted through forward, backward, and bidirectional predictions. The prediction errors are thresholded and accumulated into one image that represents the motion of the sequence. The motion representation is then followed by spatial-domain feature extractions. As such, the temporal dependencies are eliminated and the whole video sequence is represented by a few coefficients. The linear separability of the extracted features is assessed, and its suitability for both parametric and nonparametric classification techniques is elaborated upon. The proposed feature-extraction scheme was complemented by simple classification techniques, namely, K nearest neighbor (KNN) and Bayesian, i.e., likelihood ratio, classifiers. Experimental results showed classification performance ranging from 97% to 100% recognition rates. To validate our proposed technique, we have conducted a series of experiments using the classical way of classifying data with temporal dependencies, namely, hidden Markov models (HMMs). Experimental results revealed that the proposed feature-extraction scheme combined with simple KNN or Bayesian classification yields comparable results to the classical HMM-based scheme. Moreover, since the proposed scheme compresses the motion information of an image sequence into a single image, it allows for using simple classification techniques where the temporal dimension is eliminated. This is actually advantageous for both computational and storage requirements of the classifier.IEEE2021-03-14T09:59:05Z2021-03-14T09:59:05Z2007Peer-ReviewedPostprintinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfT. Shanableh, K. Assaleh and M. Al-Rousan, "Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language," in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 37, no. 3, pp. 641-650, June 2007, doi: 10.1109/TSMCB.2006.889630.1941-0492http://hdl.handle.net/11073/2136310.1109/TSMCB.2006.889630en_UShttps://doi.org/10.1109/TSMCB.2006.889630oai:repository.aus.edu:11073/213632024-08-22T12:08:21Z
spellingShingle Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language
Shanableh, Tamer
Feature extraction
Motion analysis
Pattern classification
Visual languages
status_str publishedVersion
title Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language
title_full Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language
title_fullStr Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language
title_full_unstemmed Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language
title_short Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language
title_sort Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language
topic Feature extraction
Motion analysis
Pattern classification
Visual languages
url http://hdl.handle.net/11073/21363