Regular Articles

Multi-channel and multi-scale mid-level image representation for scene classification

[+] Author Affiliations
Jinfu Yang, Fei Yang, Mingai Li

Beijing University of Technology, Faculty of Information Technology, Beijing, China

Guanghui Wang

University of Kansas, Department of Electrical Engineering and Computer Science, Lawrence, Kansas, United States

J. Electron. Imaging. 26(2), 023018 (Apr 11, 2017). doi:10.1117/1.JEI.26.2.023018
History: Received September 27, 2016; Accepted March 20, 2017
Text Size: A A A

Abstract.  Convolutional neural network (CNN)-based approaches have received state-of-the-art results in scene classification. Features from the output of fully connected (FC) layers express one-dimensional semantic information but lose the detailed information of objects and the spatial information of scene categories. On the contrary, deep convolutional features have been proved to be more suitable for describing an object itself and the spatial relations among objects in an image. In addition, the feature map from each layer is max-pooled within local neighborhoods, which weakens the invariance of global consistency and is unfavorable to scenes with highly complicated variation. To cope with the above issues, an orderless multi-channel mid-level image representation on pre-trained CNN features is proposed to improve the classification performance. The mid-level image representation of two channels from the FC layer and the deep convolutional layer are integrated at multi-scale levels. A sum pooling approach is also employed to aggregate multi-scale mid-level image representation to highlight the importance of the descriptors beneficial for scene classification. Extensive experiments on SUN397 and MIT 67 indoor datasets demonstrate that the proposed method achieves promising classification performance.

Figures in this Article
© 2017 SPIE and IS&T

Citation

Jinfu Yang ; Fei Yang ; Guanghui Wang and Mingai Li
"Multi-channel and multi-scale mid-level image representation for scene classification", J. Electron. Imaging. 26(2), 023018 (Apr 11, 2017). ; http://dx.doi.org/10.1117/1.JEI.26.2.023018


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.