摘要

At present, the common online signature verification systems adopt the contacted model of signing on a tablet or a phone screen, which have a great dependence on the device. Considering that the development of biometrics tends to the long distance and non-contact mode, a novel video-based system for in-air signature verification is proposed. First, the fingertip tracking is used for generating unique signature trajectory from the in-air signing videos. In combination of contrapuntally improved dynamic time warping (DTW) method, the Fast Fourier Transform (FFT) and the analysis on the signature length, a Gaussian distribution-based fusion algorithm is proposed for in-air signature verification. Finally, comprehensive experiments are conducted on a self-built database consisting of 560 signatures, then a false rejection rate (FRR) of 2.86% and a false acceptance rate (FAR) of 1.90% are achieved with an average matching time of only 24 ms, which have demonstrated the effectiveness of our proposed system.