Colombian Sign Language Classification Based on Hands Pose and Machine Learning Techniques Capítulo

Nombre del libro

Smart Technologies, Systems and Applications - 3rd International Conference, SmartTech-IC 2022, Revised Selected Papers

editorial

Springer Science and Business Media Deutschland GmbH

Thesis author

Anderssen Vera Maldonado
Cindy Pérez
José F. Sánchez

Resumen

New technologies can improve the inclusion of deaf (and hearing loss) people in different scenarios. In the present work, a classification of the Colombian sign language alphabet was implemented. For this, the employment of the media-pipe hands pose tool was used to feature extraction process. Then, three machine learning models: support vector classifiers, artificial neural networks and random forest, were trained to determine the best proposal. Results show how a neural network with one hidden layer obtained the best performance with 99.41%. The support vector classifier reached an accuracy of 99.12%, and the worse result was achieved by the random forest model with 96.67% in the classification. The proposal can contribute with advances in the sign language recognition in the Colombian context, which has been worked in different approaches with more complex models to do similar classifications.

autores

http://vivoweb.org/ontology/core#FacultyMember
Orjuela Cañón, Alvaro David

fecha de publicación

2023-1-1

Área temática

Salud y bienestar

Identificador de objeto digital (DOI)

https://doi.org/10.1007/978-3-031-32213-6_11

Número Estándar Internacional de Libros (ISBN)

9783031322129

Número de páginas

12

Página inicial

149

Última página

160