A Comprehensive Survey on Various Semantic Based Video/Image Retrieval Techniques
Tamil Priya D1, Divya Udayan J2
1Tamil Priya D, M.E Assistant Professor, Department of Computer Science and Engineering, Anna University, Information Technology, VIT University, Vellore (Tamil Nadu), India.
2Divya Udayan J, PHD. Associate Professor, Department of Internet and Multimedia Engineering, Konkuk University, Information Technology, VIT University, Vellore (Tamil Nadu), India.
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 185-196 | Volume-8 Issue-6, April 2019 | Retrieval Number: F3638048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Semantic Based Video/Image Retrieval is a Most critical issue in the multimedia search enginerelated research. Multimedia content annotation improves the accuracy of semantic based content retrieval system where multimedia content annotation can be done in two ways: One is content based annotation and another is context based annotation. The content based annotation of images and videos consist of both low level and high level features which would be derived from the detailed pixel intensity information of images whereas context information would provide the semantic details about the images/videos. In this analysis work, discussion about the various techniques used to retrieve the multimedia content from the web engines with the semantic knowledge awareness is provided. The various research methods that intend to perform the annotation on multimedia contents is discussed in detailed. And also, this analysis work provides the discussion about the techniques in terms of their merits and demerits. Finally this work also provides the numerical evaluation of eachtechnique based on their accuracy in the videoretrieval outcome. The overall evaluation of the surveyed methodologies is performed and provides discussion about the outcome obtained from each technique.
Keyword: Semantic Based Video Retrieval System, Context Information, Content Information, Low Level Feature, High Level Features, and Image Annotation.
Scope of the Article: Signal and Image Processing