Artificial neural networks based symbolic gesture interface

The purpose of the developed system is the realization of a gesture recognizer, applied to a user interface. We tried to get fast and easy software for user, without leaving out reliability and using instruments available to common user: a PC and a webcam. The gesture detection is based on well-known artificial vision techniques, as the tracking algorithm by Lucas and Kanade. The paths, opportunely selected, are recognized by a double layered architecture of multilayer perceptrons. The realized system is efficiency and has a good robustness, paying attention to an adequate learning of gesture vocabulary both for the user and for system.