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.

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

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)