Self-supervised learning for medieval handwriting identification: A case study from the Vatican Apostolic Library

作者：

Highlights：

• Self-supervised learning improves handwriting identification on medieval manuscripts.

• Self-supervision effectively addresses labeled data scarcity in digital paleography.

• Self-supervised pretraining enhances the model generalization to new scribes.

• Self-supervised features outperform general-domain ones on handwriting identification.

摘要

•Self-supervised learning improves handwriting identification on medieval manuscripts.•Self-supervision effectively addresses labeled data scarcity in digital paleography.•Self-supervised pretraining enhances the model generalization to new scribes.•Self-supervised features outperform general-domain ones on handwriting identification.

论文关键词：Self-supervised learning,Manuscripts,Handwriting identification

论文评审过程：Received 18 October 2021, Revised 21 December 2021, Accepted 12 January 2022, Available online 9 February 2022, Version of Record 9 February 2022.

论文官网地址：https://doi.org/10.1016/j.ipm.2022.102875