Towards the design of an offline signature verifier based on a small number of genuine samples for training
作者：
Highlights：
• Novel Offline signature verification system based on run-length distribution features.
• Models trained with only genuine signatures using One Class Support Vector Machines.
• Experiments using Single Reference Signature System (SRSS) design.
• Evaluations on GPDS960 database using a multiple evaluation metrics.
• Realized performances outperform existing methods.
摘要
•Novel Offline signature verification system based on run-length distribution features.•Models trained with only genuine signatures using One Class Support Vector Machines.•Experiments using Single Reference Signature System (SRSS) design.•Evaluations on GPDS960 database using a multiple evaluation metrics.•Realized performances outperform existing methods.
论文关键词：Offline signature verification,Single Reference Signature System,Run-length distribution features,One-Class Support Vector Machine
论文评审过程：Received 26 January 2018, Revised 9 April 2018, Accepted 27 April 2018, Available online 30 April 2018, Version of Record 3 May 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.04.035
