SIAR: Signing in the Air Using Finger Tracking Technology for Authentication on Embedded System.

In this paper, we propose a novel, convenient, fast and contactless identity authentication method. We use the camera to capture the image data when the user is signing in the air. In addition, the trajectory of the finger is captured by using deep learning model on the embedded system. The trajectory of the finger is the unique signature of the user's identity. For signature verification, the dynamic time warping algorithm is adopted to compare the similarity between the current signature and the registered signature. In order to evaluate the accuracy in the experiment, we collected the trajectories of the signatures in the air, including the registered, genuine and forged signatures. The experimental results show that the proposed method has significant effects. Add to this, this paper has the commercial values of low power consumption and low cost to meet the needs of the consumer market.