Back to articles
Volume: 28 | Article ID: art00014
Using Deep Convolutional Neural Networks for Image Retrieval
  DOI :  10.2352/ISSN.2470-1173.2016.2.VIPC-231  Published OnlineFebruary 2016

In content-based image retrieval, the most challenging problem is the “semantic gap” between low-level visual features captured by machines and high-level semantic concepts perceived by human. This paper focuses on the high-level image features learning by the convolutional neural networks (CNN) in image retrieval. As a deep learning framework, CNN can extract meaningful image features in different layers, and transfer the image content into (abstract) semantic concepts. These high-level features descriptors can be better image representations than the hand-crafted feature descriptors, and further improve the image retrieval performance. The experimental results showed that layerwise learning invariant feature hierarchies in CNN is good at feature representations. Using CNN for feature extractions on CIFAR-10 and CIFAR-100 dataset, it achieved 0.707 and 0.244 of mean average precision (MAP), respectively.

Subject Areas :
Views 35
Downloads 7
 articleview.views 35
 articleview.downloads 7
  Cite this article 

Chien-Hao Kuo, Yang-Ho Chou, Pao-Chi Chang, "Using Deep Convolutional Neural Networks for Image Retrievalin Proc. IS&T Int’l. Symp. on Electronic Imaging: Visual Information Processing and Communication VII,  2016,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2016
Electronic Imaging
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA