Δημοσιεύσεις
2021
Koulierakis, Ioannis; Siolas, Georgios; Efthimiou, Eleni; Fotinea, Stavroula-Evita; Stafylopatis, Andreas
Sign boundary and hand articulation feature recognition in Sign Language videos Journal Article
In: Machine Translation, vol. 35, no. 3, pp. 323–343, 2021.
@article{koulierakis2021sign,
title = {Sign boundary and hand articulation feature recognition in Sign Language videos},
author = {Ioannis Koulierakis and Georgios Siolas and Eleni Efthimiou and Stavroula-Evita Fotinea and Andreas Stafylopatis},
doi = {10.1007/s10590-021-09271-3},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {Machine Translation},
volume = {35},
number = {3},
pages = {323--343},
publisher = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2020
Koulierakis, Ioannis; Siolas, Georgios; Efthimiou, Eleni; Fotinea, Stavroula-Evita; Stafylopatis, Andreas
Recognition of Static Features in Sign Language Using Key-Points Proceedings Article
In: Proceedings of the LREC2020 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives, pp. 123–126, 2020.
@inproceedings{koulierakis2020recognition,
title = {Recognition of Static Features in Sign Language Using Key-Points},
author = {Ioannis Koulierakis and Georgios Siolas and Eleni Efthimiou and Stavroula-Evita Fotinea and Andreas Stafylopatis},
url = {https://www.aclweb.org/anthology/2020.signlang-1.20/},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the LREC2020 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives},
pages = {123--126},
abstract = {In this paper we report on a research effort focusing on recognition of static features of sign formation in single sign videos. Three sequential models have been developed for handshape, palm orientation and location of sign formation respectively, which make use of key-points extracted via OpenPose software. The models have been applied to a Danish and a Greek Sign Language dataset, providing results around 96%. Moreover, during the reported research, a method has been developed for identifying the time-frame of real signing in the video, which allows to ignore transition frames during sign recognition processing.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper we report on a research effort focusing on recognition of static features of sign formation in single sign videos. Three sequential models have been developed for handshape, palm orientation and location of sign formation respectively, which make use of key-points extracted via OpenPose software. The models have been applied to a Danish and a Greek Sign Language dataset, providing results around 96%. Moreover, during the reported research, a method has been developed for identifying the time-frame of real signing in the video, which allows to ignore transition frames during sign recognition processing.