Authors: Farah Debbagh; Mohammed Lamine Kherfi; Mohamed Chaouki Babahenini
Addresses: Department of Computer Science and Information Technology, Faculty of Information Technologies and Communication, University of Ouargla, Ouargla, Algeria ' Department of Mathematics and Computer Science, Université du Québec à Trois-Ririères, Canada; Department of Computer Science and Information Technology, University of Ouargla, Ouargla, Algeria ' LESIA Laboratory, Department of Computer Science, University of Biskra, Biskra, Algeria
Abstract: In text-based image retrieval, matching is a technique that retrieves for a concept query Q, images annotated with Q. The result performance is very influenced by the annotation quality. Since it is difficult to have a well-annotated data set, the retrieval neglects many relevant images simply because they are not annotated with the query concept (i.e. missing problem). In this paper, we propose a solution that considerably minimises such a problem, by integrating the semantic relatedness between concepts into the retrieval. We compute the semantic relatedness between pairs of concepts from Wikipedia articles. We use term frequency - inverse collection term frequency weighting scheme and the cosine similarity. After evaluating the obtained values, using the human judgement benchmark WordSimilarity-353, we incorporated them into image retrieval task. The experimental results on Corel 5K data set clearly show the ability of the proposed method in detecting missing images, compared with matching and some literature works.
Keywords: annotation; cosine similarity; image retrieval; missing; Pearson correlation; semantic relatedness; TBIR; TF_ICTF; Wikipedia; WordSimilarity-353.
International Journal of Signal and Imaging Systems Engineering, 2017 Vol.10 No.3, pp.146 - 156
Received: 02 Oct 2016
Accepted: 21 Apr 2017
Published online: 21 Aug 2017 *