Use of Semantic Enhancements to NLP of Image Captions to Aid Image Retrieval

Author

Kesorn, Kraisak ; Poslad, Stefan

Author_Institution

Sch. of Electron. Eng. & Comput. Sci., Queen Mary Univ. of London, London, UK

fYear

2008

fDate

15-16 Dec. 2008

Firstpage

52

Lastpage

57

Abstract

This paper proposes a semantic-based create and search technique to enhance visual information retrieval. Our approach includes an ontology-based scheme for the semi-automatic annotation for image retrieval. Latent Semantic Indexing (LSI) is used in order to solve the Natural Language (NL) vagueness problem and to tolerate ontology imperfections. In addition, our framework is able to find indirect relevant concepts in images and to represent image semantics at a higher level. Experiments demonstrate that semantic-based approaches can significantly improve image retrieval.

Keywords

image representation; image retrieval; natural language processing; ontologies (artificial intelligence); image captions; image retrieval; image semantics representation; latent semantic indexing; natural language processing; natural language vagueness problem; ontology-based scheme; semantic enhancements; semiautomatic annotation; visual information retrieval; Computer science; Frequency; HTML; Image retrieval; Indexing; Information retrieval; Large scale integration; Ontologies; Uncertainty; XML; Image retrieval; Knowledge-based model; Ontology; Semantic model; Semantic retrieval;

fLanguage

English

Publisher

ieee

Conference_Titel

Semantic Media Adaptation and Personalization, 2008. SMAP '08. Third International Workshop on

Conference_Location

Prague

Print_ISBN

978-0-7695-3444-2

Type

conf

DOI

10.1109/SMAP.2008.18

Filename

4724848