Offline signature verification using a region based deep metric learning network

作者：

Highlights：

• A region based deep convolutional Siamese network is proposed for feature and metric learning in offline signature verification

• A Mutual Signature DenseNet (MSDN) is designed to extract discriminative features by interaction between two input signatures.

• Superior performance of both writer-independent and writer-dependent signature verification are reported on public datasets.

摘要

•A region based deep convolutional Siamese network is proposed for feature and metric learning in offline signature verification•A Mutual Signature DenseNet (MSDN) is designed to extract discriminative features by interaction between two input signatures.•Superior performance of both writer-independent and writer-dependent signature verification are reported on public datasets.

论文关键词：Signature verification,Convolutional siamese network,Deep metric learning,Region fusion

论文评审过程：Received 22 May 2020, Revised 3 March 2021, Accepted 27 April 2021, Available online 12 May 2021, Version of Record 28 May 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108009