Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Semantic approach to image retrieval using statistical models based on a lexical ontology

Fadzli, Syed Abdullah and Setchi, Rossitza ORCID: 2010. Semantic approach to image retrieval using statistical models based on a lexical ontology. Lecture Notes in Computer Science 6279 , pp. 240-250.

Full text not available from this repository.


The increasing amount of digital images available on the Internet has made searching, browsing, and organizing such resources a major challenge. This paper proposes a semantic approach to text-based image retrieval of manually annotated digital images. The approach uses statistical models based on Semantic DNA (SDNA) extracted from the structure of a lexical ontology called OntoRo. The approach involves three main techniques: (a) SDNA extraction, (b) word sense disambiguation using statistical models based on the extracted SDNA, and (c) applying semantic similarity measures using SDNA. The experiments performed show that the proposed approach retrieves images based on their conceptual meaning rather than the use of specific keywords in their annotations.

Item Type: Article
Status: Published
Schools: Engineering
Additional Information: Knowledge-Based and Intelligent Information and Engineering Systems: 14th International Conference, KES 2010, Cardiff, UK, September 8-10, 2010, Proceedings, Part IV
Publisher: Springer
ISSN: 0302-9743
Last Modified: 06 Jul 2023 10:10

Citation Data

Cited 6 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item