Exploring the semantics behind a collection to improve automated image annotation

Llorente, Ainhoa; Motta, Enrico and Rüger, Stefan (2009). Exploring the semantics behind a collection to improve automated image annotation. In: Multilingual Information Access Evaluation II. Multimedia Experiments, Springer.

DOI: https://doi.org/10.1007/978-3-642-15751-6_40

Abstract

The goal of this research is to explore several semantic relatedness measures that help to refine annotations generated by a baseline non-parametric density estimation algorithm. Thus, we analyse the benefits of performing a statistical correlation using the training set or using the World Wide Web versus approaches based on a thesaurus like WordNet or Wikipedia (considered as a hyperlink structure). Experiments are carried out using the dataset provided by the 2009 edition of the ImageCLEF competition, a subset of the MIR-Flickr 25k collection. Best results correspond to approaches based on statistical correlation as they do not depend on a prior disambiguation phase like WordNet and Wikipedia. Further work needs to be done to assess whether proper disambiguation schemas might improve their performance.

Viewing alternatives

Metrics

Item Actions

Export

You can export this page using these formats Digital Object Identifier - DOI