Assistive pointer device for limb impaired people: A novel Frontier Point Method for hand movement recognition

摘要

In this modern era, the use of computer technology and computing devices play significant role in every day human activities. From the disabled people perspective, there is huge demand to improve Human-Computer Interaction (HCI), to overcome their difficulty in using the standard interactive devices. Basically, HCI provides a way for humans to interact with a computer using a keyboard, a mouse, and other input devices in real-time. This paper proposes a novel assistive pointer device called Frontier Point method (FPM), which is based on a hand movement recognition technique. The proposed hand movement recognition technique primarily focuses on the direction of hand movement for dynamic recognition in real-time using least square fitting and virtual frame techniques. Next based on boundary values, such that if the hand crosses a boundary value of a given quadrant, then a SENDKEY stroke is generated that corresponds to that range. This method is implemented with the help of a depth sensor camera called Kinect. Kinect takes the RGB data and depth data of the human skeleton and generates coordinate information corresponding to specific body joints. Experiments were conducted in which different users were evaluated for their ability to navigate a PowerPoint presentation multiple times. Collectively, an average recognition time of 2.386 s was calculated with an average recognition rate of 97.37%.