Online signature verification by continuous wavelet transformation of speed signals
作者：
Highlights：
• We proposed a novel online signature validation system using signature frequencies.
• A hidden subsystem extracts the displacement data disregarding the signature shape.
• Speed signal is extracted from the data to be transformed by CWT and trained by SVM.
• EER of 3.41% with 1.67% FNR and 3.33% FPR are achieved for 120 trials.
• Similar results are achieved by the samples taken from SVC2004 and SUSIG datasets.
摘要
•We proposed a novel online signature validation system using signature frequencies.•A hidden subsystem extracts the displacement data disregarding the signature shape.•Speed signal is extracted from the data to be transformed by CWT and trained by SVM.•EER of 3.41% with 1.67% FNR and 3.33% FPR are achieved for 120 trials.•Similar results are achieved by the samples taken from SVC2004 and SUSIG datasets.
论文关键词：Online signature verification,Biometrics,Forensics,Continuous wavelet transformation,SVM
论文评审过程：Received 2 September 2017, Revised 14 February 2018, Accepted 9 March 2018, Available online 14 March 2018, Version of Record 28 March 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.03.023
