A user-independent sensor gesture interface for embedded device

Sensor based gesture interaction gains increasing attention in ubiquitous computing; however most algorithms suffer from large database for training and user dependency limitation. This paper summarize the gesture generating model, and propose a new physical analysis based gesture recognition method which can fulfill user-independent no-training gesture recognition. It utilizes principle component analysis for energy distribution analysis to bypass the gratitude influence, and extracts the physical characteristics of the gesture trajectory for classification. In our real-time gesture recognition system, first the acceleration data of a gesture is collected through Bluetooth interface between Wii-Remote and PC; then the energy distribution shape is calculated, then several physical trajectory characteristic is organized as motion feature cascade classification. The proposed method is compared with the published method under the Nokia dataset, whose recognition accuracy could achieve 97.35% for user-independent situation.