Deep adaptive learning for writer identification based on single handwritten word images

作者：

Highlights：

• We present a method for writer identification based on single handwritten word images.

• High-level features learned from the auxiliary task are transferred to the task of writer identification in a multi-task learning framework.

• We evaluate the deep adaptive learning with three auxiliary tasks: word content, word length and character attribute recognition.

摘要

•We present a method for writer identification based on single handwritten word images.•High-level features learned from the auxiliary task are transferred to the task of writer identification in a multi-task learning framework.•We evaluate the deep adaptive learning with three auxiliary tasks: word content, word length and character attribute recognition.

论文关键词：Writer identification,Deep adaptive learning,Handwritten word attributes,Multi-task learning

论文评审过程：Received 7 November 2017, Revised 28 September 2018, Accepted 7 November 2018, Available online 8 November 2018, Version of Record 12 November 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.11.003