String representations and distances in deep Convolutional Neural Networks for image classification

作者：

Highlights：

• A structural representation of images on top of CNN features is proposed.

• Images are represented as strings to integrate spatial relationships.

• We introduce tailored string edit distances to compare images represented as strings.

• Experiments show that our structural approach is more powerful than existing ones.

• It also outperforms state-of-the-art CNN-based classification methods.

摘要

Highlights•A structural representation of images on top of CNN features is proposed.•Images are represented as strings to integrate spatial relationships.•We introduce tailored string edit distances to compare images represented as strings.•Experiments show that our structural approach is more powerful than existing ones.•It also outperforms state-of-the-art CNN-based classification methods.

论文关键词：Convolutional Neural Network,String representation,Edit distance,Image classification

论文评审过程：Received 5 March 2015, Revised 28 December 2015, Accepted 8 January 2016, Available online 21 January 2016, Version of Record 27 February 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.01.007