Extracting Multiple Features for Dynamic Hand Gesture Recognition

In this work a framework based on histogram of orientation optical flow (HOOF) and local binary pattern from three orthogonal planes (LBP_TOP) is proposed for recognizing dynamic hand gestures. HOOF algorithm extracts shape motion information gestures image sequences descriptor LBP extended to create an efficient descriptor. These features are invariant scale, translation, illumination direction motion. The performance the new tested in two different ways. first one by fusing global as other using separately train multi class support vector machine. Performance analysis shows that approach produces better results when compared with state art methods