Towards a semantics representation framework for narrative images
| Pages | 386-400 |
| Date | 03 June 2019 |
| DOI | https://doi.org/10.1108/EL-09-2018-0187 |
| Published date | 03 June 2019 |
| Author | Xuhui Li,Yanqiu Wu,Xiaoguang Wang,Tieyun Qian,Liang Hong |
| Subject Matter | Information & knowledge management,Information & communications technology,Internet |
Towards a semantics
representation framework for
narrative images
Xuhui Li,Yanqiu Wu and Xiaoguang Wang
School of Information Management, Wuhan University, Wuhan, Hubei, China
Tieyun Qian
School of Computer Science, Wuhan University, Wuhan, Hubei, China, and
Liang Hong
Shenzhen Research Institute, Wuhan University, Shenzhen, Guangdong, China
Abstract
Purpose –The purpose of this paper is to explore a semantics representation framework for narrative
images, conformingto the image-interpretation process.
Design/methodology/approach –This paper explores the essential featuresof semantics evolution in
the process of narrative images interpretation. It proposes a novel semantics representation framework,
ESImage (evolution semanticsof image) for narrative images. ESImage adopts a hierarchical architecture to
progressivelyorganize the semantic information in images, enablingthe evolutionary interpretation under the
support of a graph-based semantics data model. Also,the study shows the feasibility of this framework by
addressingthe issues of typical semantics representation with the scenarioof the Dunhuang fresco.
Findings –The process of image interpretation mainly concerns three issues: bottom-up description, the
multi-facetedsemantics representation and the top-down semanticscomplementation. ESImage can provide a
comprehensive solution for narrativeimage semantics representation by addressing the major issues based
on the semanticsevolution mechanisms of the graph-based semantics data model.
Research limitations/implications –ESImage needs to be combined with machinelearning to meet
the requirementsof automatic annotation and semantics interpretationof large-scale image resources.
Originality/value –This paper sorts out the characteristics of the gradual interpretation of narrative
images and has discussed the major issues in its semantics representation. Also, it proposes the semantic
framework ESImagewhich deploys a flexible and sound mechanism to represent the semantic informationof
narrativeimages.
Keywords Semantics, Semantics representation, Narrative images, Semantic data model
Paper type Research paper
1. Introduction
Anarrative image is an image whichdeploys visual components to narrate an eventor some
events (Lei and Wang, 2017). In the long course of human history, narrative images have
been an important medium to record historical eventsor to present fictional stories. Recent
years have seen the rapid development of storing narrative image resources, along with
This research is supported by the NSF of China under contract Nos 91646206,71420107026 and
61572376; Major Program of Key Research Institute on Humanities and Social Science of the Chinese
Ministry of Education under contract No 16JJD870002; and Basic Research Project, Shenzhen Science
and Technology Program under contract No JCYJ20160523160953223.
EL
37,3
386
Received2 October 2018
Revised6 December 2018
Accepted12 January 2019
TheElectronic Library
Vol.37 No. 3, 2019
pp. 386-400
© Emerald Publishing Limited
0264-0473
DOI 10.1108/EL-09-2018-0187
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/0264-0473.htm
To continue reading
Request your trial