Hand gesture recognition based on morphologic features

Comunicación presentada en el IX Simposium Nacional de Reconocimiento de Formas y Análisis de Imágenes, Benicàssim, Mayo, 2001.

In this paper, we try to characterize the hand posture by means of the morpho-logic coefficient, measure that allows to determine its morphology, in order to later perform its classification by means of an artificial neural network model, the Growing Cell Structure. The monitoring of the neurons that are activated for the successive postures that the hand takes throughout the time allows us to determine the gesture that is being made. Finally, we present the results of experiments with a vocabulary of 7 gestures, in order to verify the efficiency of this method of classification and extraction of characteristics.