Fine-tuning deep convolutional neural networks for distinguishing illustrations from photographs

作者：

Highlights：

• Automatically detecting illustrations is needed for the target system.

• Deep Convolutional Neural Networks have been successful in computer vision tasks.

• DCNN with fine-tuning outperformed the other models including handcrafted features.

摘要

•Automatically detecting illustrations is needed for the target system.•Deep Convolutional Neural Networks have been successful in computer vision tasks.•DCNN with fine-tuning outperformed the other models including handcrafted features.

论文关键词：Aggregation systems,Machine learning,Deep learning,Illustrations

论文评审过程：Received 14 April 2016, Revised 19 August 2016, Accepted 20 August 2016, Available online 2 September 2016, Version of Record 22 September 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.08.057