Sign Language Video Analysis For Automatic Recognition and Detection

Valentin Belissen (1, 2, 3)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
2 UP11 - Université Paris-Sud - Paris 11
3 Université Paris-Saclay

This Research Project Summary presents ongoing work on automatic Sign Language Recognition (SLR) and detection, carried out as a PhD research project at the LIMSI, CNRS, France. It uses the French part of the Dicta-Sign corpus with 8 hours of annotated dialogues from 18 native speakers [1]. This work tackles the issue of extracting relevant information from a Sign Language (SL) video, and developing systems to recognize lexical signs or even high-level linguistic features.

Mots clés: Sign Language; Convolutional Neural Networks; Recurrent Neural Networks; Sign Language Recognition

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]; Informatique [cs]

Valentin Belissen. Sign Language Video Analysis For Automatic Recognition and Detection. 14th IEEE International Conference on Automatic Face and Gesture Recognition, May 2019, Lille, France. ⟨hal-02146366⟩