Mobile Gesture Recognition

Abstract

This paper presents a methodology for a real time mobile gesture recognition system. It presents a new kind of Human - Machine interaction through mobile devices (microcontroller) and without the use of typical computer system. With the help of real time gesture recognition technologies and by using camera signal processing (web) the interaction with robotics and mechatronics systems in general can be achieved. The gestures will be continuously followed and can be directly mapped with commands of mechatronic systems such as start moving, stop moving, forward moving, backward moving etc. The proposed methodology relies on the finger gesture data acquisition, hand segmentation, fingertips localization/ identification and high-level feature extraction.