Deep learning for printed document source identification

作者：

Highlights：

• Deep learning can learn the texture features automatically.

• For microscopic documents, feature based SVM classification still performs better.

• For scanned documents, both system perform equally well with high accuracy.

摘要

•Deep learning can learn the texture features automatically.•For microscopic documents, feature based SVM classification still performs better.•For scanned documents, both system perform equally well with high accuracy.

论文关键词：Printer source identification,Machine learning,Deep learning,Convolutional neural networks

论文评审过程：Received 11 December 2017, Revised 5 August 2018, Accepted 10 September 2018, Available online 4 October 2018, Version of Record 30 October 2018.

论文官网地址：https://doi.org/10.1016/j.image.2018.09.006