Writer independent offline signature verification based on asymmetric pixel relations and unrelated training-testing datasets

作者：

Highlights：

• We perform off-line writer independent signature verification with asymmetric pixel set relations.

• We train and test blind offline signature datasets for verification.

• We apply the applicability domain in order to enhance the verification results.

摘要

•We perform off-line writer independent signature verification with asymmetric pixel set relations.•We train and test blind offline signature datasets for verification.•We apply the applicability domain in order to enhance the verification results.

论文关键词：Applicability domain,Automatic writer independent signature verification,Boosting feature selection,Decision trees,Feature extraction,Posets

论文评审过程：Received 2 July 2018, Revised 18 January 2019, Accepted 19 January 2019, Available online 27 January 2019, Version of Record 4 February 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.058