Unsupervised neural domain adaptation for document image binarization

作者：

Highlights：

• A new domain adaptation method for document image binarization.

• Modification of a state-of-the-art approach for unsupervised scenarios.

• Adaptation driven by a novel similarity measure between domains.

• Experiments with all pairwise combinations of five datasets.

• Improvement by over 42% with respect to the state of the art.

摘要

•A new domain adaptation method for document image binarization.•Modification of a state-of-the-art approach for unsupervised scenarios.•Adaptation driven by a novel similarity measure between domains.•Experiments with all pairwise combinations of five datasets.•Improvement by over 42% with respect to the state of the art.

论文关键词：Binarization,Machine learning,Domain adaptation,Adversarial training

论文评审过程：Received 3 December 2020, Revised 21 April 2021, Accepted 3 June 2021, Available online 10 June 2021, Version of Record 21 June 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108099