Options
Optimised preprocessing for automatic mouth gesture classification
Citation Link: https://doi.org/10.15480/882.3614
Publikationstyp
Conference Paper
Publikationsdatum
2020
Sprache
English
Institut
TORE-URI
Start Page
27
End Page
32
Citation
Proceedings of the 9th Workshop on the Representation and Processing of Sign Languages: 27–32 (2020)
Contribution to Conference
Publisher
European Language Resources Association (ELRA)
Mouth gestures are facial expressions in sign language, that do not refer to lip patterns of a spoken language. Research on this topic
has been limited so far. The aim of this work is to automatically classify mouth gestures from video material by training a neural
network. This could render time-consuming manual annotation unnecessary and help advance the field of automatic sign language
translation. However, it is a challenging task due to the little data available as training material and the similarity of different mouth
gesture classes. In this paper we focus on the preprocessing of the data, such as finding the area of the face important for mouth gesture
recognition. Furthermore we analyse the duration of mouth gestures and determine the optimal length of video clips for classification.
Our experiments show, that this can improve the classification results significantly and helps to reach a near human accuracy.
has been limited so far. The aim of this work is to automatically classify mouth gestures from video material by training a neural
network. This could render time-consuming manual annotation unnecessary and help advance the field of automatic sign language
translation. However, it is a challenging task due to the little data available as training material and the similarity of different mouth
gesture classes. In this paper we focus on the preprocessing of the data, such as finding the area of the face important for mouth gesture
recognition. Furthermore we analyse the duration of mouth gestures and determine the optimal length of video clips for classification.
Our experiments show, that this can improve the classification results significantly and helps to reach a near human accuracy.
Schlagworte
Sign Language Recognition/Generation
Machine Translation
SpeechToSpeech Translation
Statistical and Machine Learning Methods
DDC Class
004: Informatik
More Funding Information
This publication has been produced in the context of the joint research funding of the German Federal Government and Federal States in the Academies’ Programme, with funding from the Federal Ministry of Education and Research and the Free and Hanseatic City of Hamburg. The Academies’ Programme is coordinated by the Union of the German Academies of Sciences and Humanities.
Publication version
publishedVersion
Loading...
Name
2020.signlanglrec-1.5.pdf
Size
637.79 KB
Format
Adobe PDF