Reconocimiento de Señas Alfanuméricas de la Lengua de Señas Mexicana usando Características Tipo Haar 3D (Mexican Sign Language Alphanumerical Gestures Recognition using 3D Haar-like Features)

Javier Jimenez (javier.jimenez.villafana@gmail.com)1, Anabel Martin (amarting@correo.uady.mx)1, Victor Uc (uccetina@correo.uady.mx)1, Arturo Espinosa (eromero@correo.uady.mx)1


1Universidad Autónoma de Yucatán

This paper appears in: Revista IEEE América Latina

Publication Date: Oct. 2017
Volume: 15,   Issue: 10 
ISSN: 1548-0992


Abstract:
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 facial expressions. 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 features extracted 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 use of traditional 2D Haar-like features. Our system is able to recognize static LSM signs with a higher accuracy rate than the one obtained with widely used 2D features.

Index Terms:
Boosting, Gesture recognition, Sign language, Machine learning, 3D Haar-like features   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (610)]