Improved spatial pyramid matching for scene recognition

作者：

Highlights：

• A new spatial partition scheme combined with modified pyramid matching kernel based on spatial pyramid matching is proposed.

• Our modified spatial pyramid matching is proved to be superior to conventional spatial pyramid matching.

• We also propose a method of learning mid-level features using various autoencoders.

• Local visual descriptors are encoded into different mid-level features with sparsity, robustness and contractiveness respectively.

摘要

•A new spatial partition scheme combined with modified pyramid matching kernel based on spatial pyramid matching is proposed.•Our modified spatial pyramid matching is proved to be superior to conventional spatial pyramid matching.•We also propose a method of learning mid-level features using various autoencoders.•Local visual descriptors are encoded into different mid-level features with sparsity, robustness and contractiveness respectively.

论文关键词：Spatial pyramid matching (SPM),Spatial partition,Histogram of oriented gradients (HOG),Autoencoder,Scene recognition

论文评审过程：Received 19 May 2017, Revised 20 February 2018, Accepted 26 April 2018, Available online 27 April 2018, Version of Record 15 June 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.04.025