Detail publikace

MediaPipe and Its Suitability for Sign Language Recognition

ŠNAJDER, J. KREJSA, J.

Anglický název

MediaPipe and Its Suitability for Sign Language Recognition

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

en

Originální abstrakt

The paper presents the framework MediaPipe as a tool to extract pose features for the task of word-level isolated sign language recognition. It tests the framework’s suitability on the state-of-the-art sign language dataset AUTSL. Extracted sequences of pose features are classified by the Long Short-Term Memory recurrent neural network constructed with the TensorFlow computational library. The paper describes the proposed method flow, preprocessing of the extracted features, and training. Obtained results are then validated on test datasets, and the impact of face landmarks is evaluated. The top-1 accuracy with face landmarks is 49.89 %, while 53.21 % without them.

Anglický abstrakt

The paper presents the framework MediaPipe as a tool to extract pose features for the task of word-level isolated sign language recognition. It tests the framework’s suitability on the state-of-the-art sign language dataset AUTSL. Extracted sequences of pose features are classified by the Long Short-Term Memory recurrent neural network constructed with the TensorFlow computational library. The paper describes the proposed method flow, preprocessing of the extracted features, and training. Obtained results are then validated on test datasets, and the impact of face landmarks is evaluated. The top-1 accuracy with face landmarks is 49.89 %, while 53.21 % without them.

Klíčová slova anglicky

Sign language recognition; MediaPipe; Long Short-Term Memory; neural network; classification

Vydáno

10.05.2023

Nakladatel

Institute of Thermomechanics of the Czech Academy of Sciences

Místo

Prague

ISBN

ISBN 978-80-87012-84

ISSN

1805-8256

Kniha

ENGINEERING MECHANICS 2023

Číslo edice

1

Strany od–do

251–254

Počet stran

4

BIBTEX


@inproceedings{BUT184379,
  author="Jan {Šnajder} and Jiří {Krejsa},
  title="MediaPipe and Its Suitability for Sign Language Recognition",
  booktitle="ENGINEERING MECHANICS 2023",
  year="2023",
  month="May",
  pages="251--254",
  publisher="Institute of Thermomechanics of the Czech Academy of Sciences",
  address="Prague",
  isbn="ISBN 978-80-87012-84",
  issn="1805-8256"
}