Content and context features for scene image representation

作者：

Highlights：

• Propose a novel contextual feature extraction method for scene images.

• Propose a novel unique tokens extraction algorithm.

• Aggregate multi-scale content and contextual features to represent the scene images.

• Evaluate our proposed method on three commonly-used benchmark datasets.

摘要

•Propose a novel contextual feature extraction method for scene images.•Propose a novel unique tokens extraction algorithm.•Aggregate multi-scale content and contextual features to represent the scene images.•Evaluate our proposed method on three commonly-used benchmark datasets.

论文关键词：Image classification,Context features,Content features,Feature extraction,Machine learning,Image processing

论文评审过程：Received 7 April 2021, Revised 25 July 2021, Accepted 6 September 2021, Available online 11 September 2021, Version of Record 14 September 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107470