Research of Online Signature Recognition Based on Energy Feature
Jinxu Guo, Jianbin Zheng, Bo Lu · 2008
The paper proposes an on-line signature recognition algorithm with signature energy as feature. The signature energy features at sharp trajectory change points are extracted by means of Daubechies wavelet decomposition of signature signal. Then, 15 points with most dominant energies are chosen. Finally, a new algorithm of classification is put forward, after dynamic time warping matching, with computation amount reduced greatly. Experiment findings show that false acceptance rate is 8 percent while false rejection rate is 0 percent.