Signing as Input for a Dictionary Query: Matching Signs Based on Joint Positions of the Dominant Hand

Autor/a: FRAGKIADAKIS, Manolis; NYST, Victoria; VAN DER PUTTEN, Peter
Año: 2020
Editorial: Proceedings of the 9th Workshop on the Representation and Processing of Sign Languages, pages 69–74
Tipo de código: Copyright
Soporte: Digital


Lingüística » Lingüística de otras Lenguas de Signos


This study presents a new method to search sign language lexica, using a full sign as input for a query. Thus, a dictionary user can look up information about a sign by signing the sign to a webcam. The recorded sign is then compared to potential matching signs in the lexicon. As such, it provides a new way of searching sign language dictionaries to complement existing methods based on (spoken language) glosses or phonological features, like handshape or location. The “find the sign” method analyzes the recorded sign using OpenPose to extract the body and finger joint positions. To compare the recorded sign with the signs in the database, the variation in trajectories of the dominant hand and of the fingers is quantified and compared, using Dynamic Time Warping (DTW). The method was tested with ten people with various degrees of sign language proficiency. Each subject viewed a set of 20 out of 100 total signs from the newly compiled Ghanaian Sign Language lexicon and was asked to replicate the signs. The results show that our method can predict the matching sign with 87% and 74% accuracy at the Top-10 and Top-5 ranking level respectively by using only the trajectory of the dominant hand. Additionally, more proficient signers obtain 90% accuracy at the Top-10 ranking. The methodology has the potential to be used also as a variation measurement tool to quantify the difference in signing between different signers or sign languages in general