Discriminative feature selection for on-line signature verification
作者：
Highlights：
• On-line test signatures are aligned effectively to reference templates based on Gaussian mixture model before verification.
• Discriminative features are selected based on full factorial experiment design among consistent feature candidates.
• An alternative method of discriminative feature selection based on optimal orthogonal experiment design is presented to improve the efficiency.
• Features are not matched by DTW directly, but they are matched with the location constraints instead, which are inherent in two matching signature curves.
摘要
•On-line test signatures are aligned effectively to reference templates based on Gaussian mixture model before verification.•Discriminative features are selected based on full factorial experiment design among consistent feature candidates.•An alternative method of discriminative feature selection based on optimal orthogonal experiment design is presented to improve the efficiency.•Features are not matched by DTW directly, but they are matched with the location constraints instead, which are inherent in two matching signature curves.
论文关键词：On-line signature verification,Discriminative feature selection,Factorial experiment design,Orthogonal experiment design,Signature alignment,Signature curve constraint
论文评审过程：Received 14 April 2017, Revised 13 September 2017, Accepted 19 September 2017, Available online 27 September 2017, Version of Record 5 October 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.09.033
