Recently, researches for user interface are is being processed remarkably due to the explosive growth of 3-dimensional contents and applications, and the spread class of computer user.
This paper proposes a novel method to manipulate virtual 3D models efficiently in 3-dimensional space using only the intuitive motion of hand. Previous methods have some drawbacks such as burden of expensive device, high complexity of gesture recognition, assistance of additional information using maker, and so on. To improve the defects, we propose a novel interface based on the visual touch. In the proposed method, user can manipulate 3D models with sense of depth in the real environment because the method adopts stereo camera. So application range is expanded to 3D space 2D space to control of 3D models. Intuitive manipulation is also available because the proposed method supports visual touch for the virtual object that user want to manipulate, only using simple motions of hand. Users can also control the wanted 3D models using fingertip. Hand motion data from each frame is relatively small rather than previous method, so it has small burden about system and can classify hand motions in real time.
We analysed hand motions using the vector and variation regarding fingertips and center of hand region in each frame. We defined truth data of hand motions calculated dissimilarity via DTW algorithm to classify with input hand motions. Error estimation of hand motions was based on the difference of recognition rates for human and computer, in case of does not given hand motions. Finally, the efficiency of the proposed method is verified via an application based on our proposed interface.