Multidimensional data analysis

Abstract

Gesture interaction has become a major role as intuitive control of remote devices. Motion-based hand gesture recognition using a wearable motion sensor equipped on the wrist-band helps decreasing recognition errors compared with that of video-based recognition systems. However, the user interaction is often interrupted even in the low-error conditions because an inappropriate gesture recognition mode is applied on the system or user can't find out how to handle it using gestures. We propose a novel gesture interaction technique using visual attention to suggest user an appropriate gesture on the condition of selectable contents on the screen. We applied this interaction method on the content navigation interface for the TV and found it essential to realize natural and intuitive gesture interactions.