Table of Contents Author Guidelines Submit a Manuscript
Advances in Multimedia
Volume 2018, Article ID 6153607, 11 pages
Research Article

Combining Convolutional Neural Network and Markov Random Field for Semantic Image Retrieval

1School of Information Technology in Education, South China Normal University, Guangzhou, China
2Guangdong Engineering Research Center for Smart Learning, South China Normal University, Guangzhou, China
3School of Computing and Mathematics, Charles Sturt University, Albury, NSW, Australia
4School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China

Correspondence should be addressed to Changqin Huang; nc.ude.uncs@gnauhqc

Received 4 May 2018; Accepted 12 June 2018; Published 1 August 2018

Academic Editor: Yong Luo

Copyright © 2018 Haijiao Xu et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


With the rapidly growing number of images over the Internet, efficient scalable semantic image retrieval becomes increasingly important. This paper presents a novel approach for semantic image retrieval by combining Convolutional Neural Network (CNN) and Markov Random Field (MRF). As a key step, image concept detection, that is, automatically recognizing multiple semantic concepts in an unlabeled image, plays an important role in semantic image retrieval. Unlike previous work that uses single-concept classifiers one by one, we detect semantic multiconcept by using a multiconcept scene classifier. In other words, our approach takes multiple concepts as a holistic scene for multiconcept scene learning. Specifically, we first train a CNN as a concept classifier, which further includes two types of classifiers: a single-concept fully connected classifier that is best suited to single-concept detection and a multiconcept scene fully connected classifier that is good for holistic scene detection. Then we propose an MRF-based late fusion approach that is able to effectively learn the semantic correlation between the single-concept classifier and multiconcept scene classifier. Finally, the semantic correlation among the subconcepts of images is cought to further improve detection precision. In order to investigate the feasibility and effectiveness of our proposed approach, we conduct comprehensive experiments on two publicly available image databases. The results show that our proposed approach outperforms several state-of-the-art approaches.