Visual gesture recognition for real-time editing system

This research aims to recognize one-stroke pictorial gestures from visual images, and to develop a graphic/text editing system running in real time. The tasks are performed through three steps: moving-hand tracking and trajectory generation, key-gesture segmentation and gesture recognition by analyzing dynamic features. A gesture vocabulary consists of forty-eight gestures of three types: (1) six editing commands, (2) six graphic primitives, (3) alphanumeric characters-twenty-six alphabetic and ten numerical. Some dynamic features are obtained from spatio-temporal trajectories and quantized by the K-means algorithm. The quantized vectors were trained and tested using hidden Markov models (HMMs).