An eye-in-hand deice for hand gesture-based human-robot interaction

This paper introduces a novel vision device for hand gesture-based human-robot interaction. Taking advantage of an eye-in-hand configuration, the proposed device guarantees that a target hand is projected always onto images captured from a camera. On the basis of the device, an adaptive histogram-based hand region segmentation algorithm is also proposed especially to enhance the performance against background and illumination changes. The proposed method is evaluated through several experiments using test images.