KDEVIR at ImageCLEF 2014 Scalable Concept Image Annotation Task: Ontology-based Automatic Image Annotation
Ismat Ara Reshma, Zia Ullah, Masaki Aono · CLEF (Working Notes) · 2014
y Abstract. In this paper, we describe our participation in the Image- CLEF 2014 Scalable Concept Image Annotation task. In this partici- pation, we propose a novel approach of automatic image annotation by using ontology at several steps of supervised learning. In this regard, we construct tree-like ontology for each annotating concept of images using WordNet and Wikipedia as primary source of knowledge. The con- structed ontologies are used throughout the proposed framework includ- ing several phases of training and testing of one-vs-all SVMs classier. Experimental results clearly demonstrate the effectiveness of the pro- posed framework.