Título

Mexican sign language alphanumerical gestures recognition using 3D haar-like features

Autor

JAVIER ARMANDO JIMENEZ VILLAFAÑA

ANABEL MARTÍN GONZALEZ

VICTOR EMANUEL DE ATOCHA UC CETINA

ARTURO ESPINOSA ROMERO

Nivel de Acceso

Acceso Abierto

Licencia

http://creativecommons.org/licenses/by-nc-nd/4.0

Materias

INGENIERÍA Y TECNOLOGÍA - (CTI) Boosting - ([urn:issn:1548-0992]) Gesture recognition - ([urn:issn:1548-0992]) Sign language - ([urn:issn:1548-0992]) Machine learning - ([urn:issn:1548-0992]) 3D Haar-like features - ([urn:issn:1548-0992])

Resumen o descripción

The Mexican Sign Language (LSM) is a language of the deaf Mexican community, which consists of a series of gestural signs articulated by hands and accompanied with facialexpressions. The lack of automated systems to translate signs from LSM makes integration of hearing-impaired people to society more difficult. This work presents a new method for LSM alphanumerical signs recognition based on 3D Haar-like featuresextracted from depth images captured by the Microsoft Kinect sensor. Features are processed with a boosting algorithm. To evaluate performance of our method, we recognized a set of signs from letters and numbers, and compared the results with the useof traditional 2D Haar-like features. Our system is able to recognize static LSM signs with a higher accuracy rate than theone obtained with widely used 2D features.

Fecha de publicación

18 de octubre de 2017

Tipo de publicación

Artículo

Recurso de información

http://redi.uady.mx:8080/handle/123456789/778

Formato

application/pdf

Fuente

urn:issn:1548-0992

Idioma

Español

Cobertura

Investigación aplicada

Audiencia

Investigadores

Repositorio Orígen

Repositorio Digital Institucional de la Universidad Autónoma de Yucatán

Descargas

0