Document image binarization with cascaded generators of conditional generative adversarial networks

作者：

Highlights：

• A novel binarization method for degraded document image is presented.

• We apply cGANs strategy on document image binarization and propose a proper framework for this task.

• We solve the core problem of multi-scale information combination using cascaded sub-generators.

• Extensive experiments on various datasets show that our method is robust and effective.

摘要

•A novel binarization method for degraded document image is presented.•We apply cGANs strategy on document image binarization and propose a proper framework for this task.•We solve the core problem of multi-scale information combination using cascaded sub-generators.•Extensive experiments on various datasets show that our method is robust and effective.

论文关键词：Cascaded generator,Conditional generative adversarial networks,Document image binarization,Image generation,Historical document analysis

论文评审过程：Received 27 April 2019, Revised 4 July 2019, Accepted 12 July 2019, Available online 12 July 2019, Version of Record 23 July 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.106968