Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition

This work introduces two novel approaches for feature extraction applied to video-based Arabic sign language recognition, namely, motion representation through motion estimation and motion representation through motion residuals. In the former, motion estimation is used to compute the motion vectors...

Full description

Saved in:
Bibliographic Details
Main Author: Shanableh, Tamer (author)
Other Authors: Assaleh, Khaled (author)
Format: article
Published: 2007
Subjects:
Online Access:http://hdl.handle.net/11073/21362
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513436719775744
author Shanableh, Tamer
author2 Assaleh, Khaled
author2_role author
author_facet Shanableh, Tamer
Assaleh, Khaled
author_role author
dc.creator.none.fl_str_mv Shanableh, Tamer
Assaleh, Khaled
dc.date.none.fl_str_mv 2007
2021-03-11T09:35:31Z
2021-03-11T09:35:31Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Shanableh, T., Assaleh, K. Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition. J Image Video Proc 2007, 087929 (2007). https://doi.org/10.1155/2007/87929
1687-5281
http://hdl.handle.net/11073/21362
10.1155/2007/87929
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv Springer
dc.relation.none.fl_str_mv https://doi.org/10.1155/2007/87929
https://link.springer.com/article/10.1155/2007/87929
dc.subject.none.fl_str_mv Frequency Domain
Feature Vector
Feature extraction
Markov Model
Classification Accuracy
dc.title.none.fl_str_mv Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description This work introduces two novel approaches for feature extraction applied to video-based Arabic sign language recognition, namely, motion representation through motion estimation and motion representation through motion residuals. In the former, motion estimation is used to compute the motion vectors of a video-based deaf sign or gesture. In the preprocessing stage for feature extraction, the horizontal and vertical components of such vectors are rearranged into intensity images and transformed into the frequency domain. In the second approach, motion is represented through motion residuals. The residuals are then thresholded and transformed into the frequency domain. Since in both approaches the temporal dimension of the video-based gesture needs to be preserved, hidden Markov models are used for classification tasks. Additionally, this paper proposes to project the motion information in the time domain through either telescopic motion vector composition or polar accumulated differences of motion residuals. The feature vectors are then extracted from the projected motion information. After that, model parameters can be evaluated by using simple classifiers such as Fisher's linear discriminant. The paper reports on the classification accuracy of the proposed solutions. Comparisons with existing work reveal that up to 39% of the misclassifications have been corrected.
format article
id aus_45e111fb9959e7052088b9374c0557ec
identifier_str_mv Shanableh, T., Assaleh, K. Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition. J Image Video Proc 2007, 087929 (2007). https://doi.org/10.1155/2007/87929
1687-5281
10.1155/2007/87929
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/21362
publishDate 2007
publisher.none.fl_str_mv Springer
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language RecognitionShanableh, TamerAssaleh, KhaledFrequency DomainFeature VectorFeature extractionMarkov ModelClassification AccuracyThis work introduces two novel approaches for feature extraction applied to video-based Arabic sign language recognition, namely, motion representation through motion estimation and motion representation through motion residuals. In the former, motion estimation is used to compute the motion vectors of a video-based deaf sign or gesture. In the preprocessing stage for feature extraction, the horizontal and vertical components of such vectors are rearranged into intensity images and transformed into the frequency domain. In the second approach, motion is represented through motion residuals. The residuals are then thresholded and transformed into the frequency domain. Since in both approaches the temporal dimension of the video-based gesture needs to be preserved, hidden Markov models are used for classification tasks. Additionally, this paper proposes to project the motion information in the time domain through either telescopic motion vector composition or polar accumulated differences of motion residuals. The feature vectors are then extracted from the projected motion information. After that, model parameters can be evaluated by using simple classifiers such as Fisher's linear discriminant. The paper reports on the classification accuracy of the proposed solutions. Comparisons with existing work reveal that up to 39% of the misclassifications have been corrected.Springer2021-03-11T09:35:31Z2021-03-11T09:35:31Z2007Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfShanableh, T., Assaleh, K. Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition. J Image Video Proc 2007, 087929 (2007). https://doi.org/10.1155/2007/879291687-5281http://hdl.handle.net/11073/2136210.1155/2007/87929en_UShttps://doi.org/10.1155/2007/87929https://link.springer.com/article/10.1155/2007/87929oai:repository.aus.edu:11073/213622024-08-22T12:08:45Z
spellingShingle Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition
Shanableh, Tamer
Frequency Domain
Feature Vector
Feature extraction
Markov Model
Classification Accuracy
status_str publishedVersion
title Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition
title_full Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition
title_fullStr Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition
title_full_unstemmed Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition
title_short Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition
title_sort Telescopic Vector Composition and Polar Accumulated Motion Residuals for Feature Extraction in Arabic Sign Language Recognition
topic Frequency Domain
Feature Vector
Feature extraction
Markov Model
Classification Accuracy
url http://hdl.handle.net/11073/21362