Decision-level fusion for single-view gait recognition with various carrying and clothing conditions

Gait Recognition is one of the latest and attractive biometric techniques, due to its potential in identification of individuals at a distance, unobtrusively and even using low resolution images. In this paper we focus on single lateral view gait recognition with various carrying and clothing condit...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Al-Tayyan, Amer (author)
مؤلفون آخرون: Assaleh, Khaled (author), Shanableh, Tamer (author)
التنسيق: article
منشور في: 2017
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/11073/8817
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513443673931776
author Al-Tayyan, Amer
author2 Assaleh, Khaled
Shanableh, Tamer
author2_role author
author
author_facet Al-Tayyan, Amer
Assaleh, Khaled
Shanableh, Tamer
author_role author
dc.creator.none.fl_str_mv Al-Tayyan, Amer
Assaleh, Khaled
Shanableh, Tamer
dc.date.none.fl_str_mv 2017-05-01T05:27:19Z
2017-05-01T05:27:19Z
2017
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Al-Tayyan, A., Assaleh, K., & Shanableh, T. (2017). Decision-level fusion for single-view gait recognition with various carrying and clothing conditions. Image and Vision Computing, 61, 54-69. doi:10.1016/j.imavis.2017.02.004
0262-8856
http://hdl.handle.net/11073/8817
10.1016/j.imavis.2017.02.004
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv Elsevier
dc.relation.none.fl_str_mv http://doi.org/10.1016/j.imavis.2017.02.004
dc.subject.none.fl_str_mv Biometrics
Gait recognition
Decision-level fusion
Accumulated prediction image
Accumulated flow image
Edge-masked active energy image
Multilinear subspace learning
dc.title.none.fl_str_mv Decision-level fusion for single-view gait recognition with various carrying and clothing conditions
dc.type.none.fl_str_mv Postprint
Peer-Reviewed
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description Gait Recognition is one of the latest and attractive biometric techniques, due to its potential in identification of individuals at a distance, unobtrusively and even using low resolution images. In this paper we focus on single lateral view gait recognition with various carrying and clothing conditions. Such a system is needed in access control applications whereby a single view is imposed by the system setup. The gait data is firstly processed using three gait representation methods as the features sources; Accumulated Prediction Image (API) and two new gait representations namely; Accumulated Flow Image (AFI) and Edge-Masked Active Energy Image (EMAEI). Secondly, each of these methods is tested using three matching classification schemes; image projection with Linear Discriminant Functions (LDF), Multilinear Principal Component Analysis (MPCA) with K-Nearest Neighbor (KNN) classifier and the third method: MPCA plus Linear Discriminant Analysis (MPCA+LDA) with KNN classifier. Gait samples are fed into the MPCA and MPCALDA algorithms using a novel tensor-based form of the gait images. This arrangement results into nine recognition subsystems. Decisions from the nine classifiers are fused using decision-level (majority voting) scheme. A comparison between unweighted and weighted voting schemes is also presented. The methods are evaluated on CASIA B Dataset using four different experimental setups, and on OU-ISIR Dataset B using two different setups. The experimental results show that the classification accuracy of the proposed methods is encouraging and outperforms several state-of-the-art gait recognition approaches reported in the literature.
format article
id aus_794c56a2bf393e5daaab755dcfd5b6a3
identifier_str_mv Al-Tayyan, A., Assaleh, K., & Shanableh, T. (2017). Decision-level fusion for single-view gait recognition with various carrying and clothing conditions. Image and Vision Computing, 61, 54-69. doi:10.1016/j.imavis.2017.02.004
0262-8856
10.1016/j.imavis.2017.02.004
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/8817
publishDate 2017
publisher.none.fl_str_mv Elsevier
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Decision-level fusion for single-view gait recognition with various carrying and clothing conditionsAl-Tayyan, AmerAssaleh, KhaledShanableh, TamerBiometricsGait recognitionDecision-level fusionAccumulated prediction imageAccumulated flow imageEdge-masked active energy imageMultilinear subspace learningGait Recognition is one of the latest and attractive biometric techniques, due to its potential in identification of individuals at a distance, unobtrusively and even using low resolution images. In this paper we focus on single lateral view gait recognition with various carrying and clothing conditions. Such a system is needed in access control applications whereby a single view is imposed by the system setup. The gait data is firstly processed using three gait representation methods as the features sources; Accumulated Prediction Image (API) and two new gait representations namely; Accumulated Flow Image (AFI) and Edge-Masked Active Energy Image (EMAEI). Secondly, each of these methods is tested using three matching classification schemes; image projection with Linear Discriminant Functions (LDF), Multilinear Principal Component Analysis (MPCA) with K-Nearest Neighbor (KNN) classifier and the third method: MPCA plus Linear Discriminant Analysis (MPCA+LDA) with KNN classifier. Gait samples are fed into the MPCA and MPCALDA algorithms using a novel tensor-based form of the gait images. This arrangement results into nine recognition subsystems. Decisions from the nine classifiers are fused using decision-level (majority voting) scheme. A comparison between unweighted and weighted voting schemes is also presented. The methods are evaluated on CASIA B Dataset using four different experimental setups, and on OU-ISIR Dataset B using two different setups. The experimental results show that the classification accuracy of the proposed methods is encouraging and outperforms several state-of-the-art gait recognition approaches reported in the literature.Elsevier2017-05-01T05:27:19Z2017-05-01T05:27:19Z2017PostprintPeer-Reviewedinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfAl-Tayyan, A., Assaleh, K., & Shanableh, T. (2017). Decision-level fusion for single-view gait recognition with various carrying and clothing conditions. Image and Vision Computing, 61, 54-69. doi:10.1016/j.imavis.2017.02.0040262-8856http://hdl.handle.net/11073/881710.1016/j.imavis.2017.02.004en_UShttp://doi.org/10.1016/j.imavis.2017.02.004oai:repository.aus.edu:11073/88172024-08-22T12:08:40Z
spellingShingle Decision-level fusion for single-view gait recognition with various carrying and clothing conditions
Al-Tayyan, Amer
Biometrics
Gait recognition
Decision-level fusion
Accumulated prediction image
Accumulated flow image
Edge-masked active energy image
Multilinear subspace learning
status_str publishedVersion
title Decision-level fusion for single-view gait recognition with various carrying and clothing conditions
title_full Decision-level fusion for single-view gait recognition with various carrying and clothing conditions
title_fullStr Decision-level fusion for single-view gait recognition with various carrying and clothing conditions
title_full_unstemmed Decision-level fusion for single-view gait recognition with various carrying and clothing conditions
title_short Decision-level fusion for single-view gait recognition with various carrying and clothing conditions
title_sort Decision-level fusion for single-view gait recognition with various carrying and clothing conditions
topic Biometrics
Gait recognition
Decision-level fusion
Accumulated prediction image
Accumulated flow image
Edge-masked active energy image
Multilinear subspace learning
url http://hdl.handle.net/11073/8817