AUTHOR=Bigand Félix , Prigent Elise , Berret Bastien , Braffort Annelies 

TITLE=Machine Learning of Motion Statistics Reveals the Kinematic Signature of the Identity of a Person in Sign Language

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2021.710132

DOI=10.3389/fbioe.2021.710132

ISSN=2296-4185

ABSTRACT=Sign language motion contains information about the identity of a signer, as does voice for a speaker or gait for a walker. However, how such information is encoded in the person's movements remains unclear. In the present study, a machine learning model was trained to extract the motion features allowing for the automatic identification of signers. A motion capture (mocap) system recorded 6 signers during the spontaneous production of French Sign Language discourses. A Principal Component Analysis was applied to time-averaged statistics of the mocap data. A linear classifier then managed to identify the signers from a reduced set of principal components.  The performance of the model was not affected when information about size and shape of the signers were normalized. Posture normalization decreased the performance of the model, which nevertheless remained over five times superior to chance level. These findings demonstrate that a signer’s identity can be characterized by specific statistics of kinematic features, beyond information related to size, shape and posture. This is a first step toward determining the motion descriptors necessary to account for human ability to identify signers.