Perceptual user interface using gesture recognition

One step towards the realization of a PUI (perceptual user interface)for robot control is the creation of VBI (View-Based Interface) projects, which consist of several image processing algorithms to handle user tracking, face tracking/pose estimation, 3D articulated body tracking, and appearance-based gesture recognition. From this viewpoint, we have studied an on-line gesture recognition technique for robot control using several image processing and recognition modeling algorithms. The following three phases are applied for the recognition of our gestures The first step is the definition of a spotting algorithm to detect the start and end position from a series of natural arm/body motions The second step is an effective feature extraction method for recognizing various gestures. The third step is to make a recognition model based on a knowledge-based system.