From text to signatures: Knowledge transfer for efficient deep feature learning in offline signature verification

作者：

Highlights：

• Offline writer dependent signature verification using deep feature learning.

• Convolutional neural network is trained in handwritten text identification.

• Feature mapping through metric learning stage that utilizes contrastive loss.

• State-of-the-art performance with much less training signature samples.

• Skilled forgeries are not required at any training stage of the proposed system.

摘要

•Offline writer dependent signature verification using deep feature learning.•Convolutional neural network is trained in handwritten text identification.•Feature mapping through metric learning stage that utilizes contrastive loss.•State-of-the-art performance with much less training signature samples.•Skilled forgeries are not required at any training stage of the proposed system.

论文关键词：Offline Signature Verification,Handwriting,Deep learning approach,Transfer learning,Metric learning

论文评审过程：Received 13 January 2021, Revised 20 October 2021, Accepted 20 October 2021, Available online 31 October 2021, Version of Record 8 November 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116136