Movement of Hand Motion Trajectory through Mid-Air using Stroke Technique

In this paper, we propose a regular HCI mid-air based method based on trajectory motion. A key issue in distinguishing uninterrupted gestures is that performance of predictable algorithms is slower through this method, without knowing initial and destination of a gesture or differences in gesture interval. These issues become particularly difficult for those methods that rely on time- based information. For the improvement the issues of regular gesture recognition, we propose a outline that simultaneously performs both segmentation and 3D form of the motion with Depth Sensing Camera. The movement of the hand motion store in the frames through video and improve the performance and correctness of the gesture with large time-based deviation. Gesture trajectories perform a single stroke in the frame of hand movement in angular form. Dynamic trajectory segment varied in various frames with DTW to improve the Performance. For recognition, these trajectory segments are examined to determine whether the segment belongs to a class among intended gestures or a non-gesture class based on fusion of shape information and temporal features. In order to assess performance, the proposed algorithm was evaluated with a database of digit hand gestures. The experimental results indicate that the proposed algorithm has a high recognition rate while maintaining its performance in the presence of continuous gestures.