Thai sign language translation using scale invariant feature transform and hidden markov models

Visual communication is important for a deft and/or mute person. It is also one of the tools for the communication between human and machines. In this paper, we develop an automatic Thai sign language translation system that is able to translate sign language that is not finger-spelling sign languag...

Full description

Saved in:
Bibliographic Details
Main Authors: Auephanwiriyakul S., Phitakwinai S., Suttapak W., Chanda P., Theera-Umpon N.
Format: Article
Language:English
Published: 2014
Online Access:http://www.scopus.com/inward/record.url?eid=2-s2.0-84878059124&partnerID=40&md5=33ef5ac9f1bfac7aba9b21e8c6451935
http://cmuir.cmu.ac.th/handle/6653943832/1626
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
Language: English
id th-cmuir.6653943832-1626
record_format dspace
spelling th-cmuir.6653943832-16262014-08-29T09:29:32Z Thai sign language translation using scale invariant feature transform and hidden markov models Auephanwiriyakul S. Phitakwinai S. Suttapak W. Chanda P. Theera-Umpon N. Visual communication is important for a deft and/or mute person. It is also one of the tools for the communication between human and machines. In this paper, we develop an automatic Thai sign language translation system that is able to translate sign language that is not finger-spelling sign language. In particular, we utilize Scale Invariant Feature Transform (SIFT) to match a test frame with observation symbols from keypoint descriptors collected in the signature library. These keypoint descriptors are computed from several keyframes that are recorded at different times of day for several days from five subjects. Hidden Markov Models (HMMs) are then used to translate observation sequences to words. We also collect Thai sign language videos from 20 subjects for testing. The system achieves approximately 86-95% for signer-dependent on the average, 79.75% for signer-semi-independent (same subjects used in the HMM training only) on the average and 76.56% for signer-independent on the average. These results are from the constrained system in which each signer wears a shirt with long sleeves in front of dark background. The unconstrained system in which each signer does not wear a long-sleeve shirt in front of various natural backgrounds yields a good result of around 74% on the average on the signer-independent experiment. The important feature of the proposed system is the consideration of shapes and positions of fingers, in addition to hand information. This feature provides the system ability to recognize the hand sign words that have similar gestures. © 2013 Elsevier B.V. All rights reserved. 2014-08-29T09:29:32Z 2014-08-29T09:29:32Z 2013 Article 01678655 10.1016/j.patrec.2013.04.017 http://www.scopus.com/inward/record.url?eid=2-s2.0-84878059124&partnerID=40&md5=33ef5ac9f1bfac7aba9b21e8c6451935 http://cmuir.cmu.ac.th/handle/6653943832/1626 English
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
language English
description Visual communication is important for a deft and/or mute person. It is also one of the tools for the communication between human and machines. In this paper, we develop an automatic Thai sign language translation system that is able to translate sign language that is not finger-spelling sign language. In particular, we utilize Scale Invariant Feature Transform (SIFT) to match a test frame with observation symbols from keypoint descriptors collected in the signature library. These keypoint descriptors are computed from several keyframes that are recorded at different times of day for several days from five subjects. Hidden Markov Models (HMMs) are then used to translate observation sequences to words. We also collect Thai sign language videos from 20 subjects for testing. The system achieves approximately 86-95% for signer-dependent on the average, 79.75% for signer-semi-independent (same subjects used in the HMM training only) on the average and 76.56% for signer-independent on the average. These results are from the constrained system in which each signer wears a shirt with long sleeves in front of dark background. The unconstrained system in which each signer does not wear a long-sleeve shirt in front of various natural backgrounds yields a good result of around 74% on the average on the signer-independent experiment. The important feature of the proposed system is the consideration of shapes and positions of fingers, in addition to hand information. This feature provides the system ability to recognize the hand sign words that have similar gestures. © 2013 Elsevier B.V. All rights reserved.
format Article
author Auephanwiriyakul S.
Phitakwinai S.
Suttapak W.
Chanda P.
Theera-Umpon N.
spellingShingle Auephanwiriyakul S.
Phitakwinai S.
Suttapak W.
Chanda P.
Theera-Umpon N.
Thai sign language translation using scale invariant feature transform and hidden markov models
author_facet Auephanwiriyakul S.
Phitakwinai S.
Suttapak W.
Chanda P.
Theera-Umpon N.
author_sort Auephanwiriyakul S.
title Thai sign language translation using scale invariant feature transform and hidden markov models
title_short Thai sign language translation using scale invariant feature transform and hidden markov models
title_full Thai sign language translation using scale invariant feature transform and hidden markov models
title_fullStr Thai sign language translation using scale invariant feature transform and hidden markov models
title_full_unstemmed Thai sign language translation using scale invariant feature transform and hidden markov models
title_sort thai sign language translation using scale invariant feature transform and hidden markov models
publishDate 2014
url http://www.scopus.com/inward/record.url?eid=2-s2.0-84878059124&partnerID=40&md5=33ef5ac9f1bfac7aba9b21e8c6451935
http://cmuir.cmu.ac.th/handle/6653943832/1626
_version_ 1681419705560072192