Share Email Print

Proceedings Paper

Mexican sign language recognition using normalized moments and artificial neural networks
Author(s): J-Francisco Solís-V.; Carina Toxqui-Quitl; David Martínez-Martínez; Margarita H.-G.
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This work presents a framework designed for the Mexican Sign Language (MSL) recognition. A data set was recorded with 24 static signs from the MSL using 5 different versions, this MSL dataset was captured using a digital camera in incoherent light conditions. Digital Image Processing was used to segment hand gestures, a uniform background was selected to avoid using gloved hands or some special markers. Feature extraction was performed by calculating normalized geometric moments of gray scaled signs, then an Artificial Neural Network performs the recognition using a 10-fold cross validation tested in weka, the best result achieved 95.83% of recognition rate.

Paper Details

Date Published: 19 September 2014
PDF: 5 pages
Proc. SPIE 9216, Optics and Photonics for Information Processing VIII, 92161A (19 September 2014); doi: 10.1117/12.2061077
Show Author Affiliations
J-Francisco Solís-V., Univ. Autónoma del Estado de México (Mexico)
Carina Toxqui-Quitl, Univ. Politécnica de Tulancingo (Mexico)
David Martínez-Martínez, Univ. Autónoma del Estado de México (Mexico)
Margarita H.-G., Univ. Autónoma del Estado de México (Mexico)

Published in SPIE Proceedings Vol. 9216:
Optics and Photonics for Information Processing VIII
Abdul A. S. Awwal; Khan M. Iftekharuddin; Mohammad A. Matin; Andrés Márquez, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?