A method of dynamic hand gesture detection based on local background updates and skin color model

摘要

Aim at the faults of the traditional background difference method based on Bayes Rule when detects motion hand gestures, such as the existence of interference regions, slow computing speed and so on. A method of dynamic hand gesture detection based on local background updates and skin color model is proposed in this paper. The skin color region in a single image is extracted through skin color model to remove interference objects, and computing speed is improved through local background updates. The experimental results show that this method can preferably detect out motion hand gestures even in complex background.