Scene image representation by foreground, background and hybrid features

作者：

Highlights：

• We identify foreground, background, and hybrid deep features for scene images.

• We aggregate all three types of deep features to represent the scene images.

• We evaluate our proposed method using two commonly used benchmark datasets.

摘要

•We identify foreground, background, and hybrid deep features for scene images.•We aggregate all three types of deep features to represent the scene images.•We evaluate our proposed method using two commonly used benchmark datasets.

论文关键词：Image processing,Machine learning,Classification,Deep learning,Image representation,Hybrid features

论文评审过程：Received 18 June 2020, Revised 21 March 2021, Accepted 23 May 2021, Available online 29 May 2021, Version of Record 1 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115285