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.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
J-Francisco Solís-V. ; Carina Toxqui-Quitl ; David Martínez-Martínez and Margarita H.-G.
Mexican sign language recognition using normalized moments and artificial neural networks
", Proc. SPIE 9216, Optics and Photonics for Information Processing VIII, 92161A (September 19, 2014); doi:10.1117/12.2061077; http://dx.doi.org/10.1117/12.2061077