Current approaches to automatic, class speciﬁc, image retrieval from the World Wide Web (WWW) by linguistic query often make use of an image’s internal characteristics and ﬁle meta-data to augment and improve result accuracy. We propose that, in extension, improvement can be achieved in relevance, noise-reduction and completeness through sense disambiguation and contextual meta-data prepossessing. Our schemes exploits a linguistic ontology identifying query relevant homographs used to construct sense speciﬁc keyword sets allowing for enhanced image search and result ranking via the calculation of relatedness between query homographs and image context prior to any additional ﬁltering. Within the paper we investigate different schemes for keyword set construction; ontology exclusive and authority extended, along with three differing ranking mechanisms.
|Translated title of the contribution||Improving Image Sets Through Sense Disambiguation and Context Ranking|
|Title of host publication||2009 IEEE International Conference on Systems, Man and Cybernetics (SMC 2009)|
|Subtitle of host publication||Proceedings of a meeting held 11-14 October 2009, San Antonio, Texas|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Number of pages||8|
|Publication status||Published - Jan 2010|