Image Retrieval through Qualitative Representations over Semantic Features

Abstract

We propose a qualitative knowledge-driven semantic modelling approach for image retrieval based on qualitative relations over local semantic concepts of images. The relative similarity of two images is proportional to their qualitative similarity. The similarity measure is calculated for each query by exploiting the notion of conceptual neighbourhood – a measure of closeness between qualitative relations. The approach is motivated by the need to perform semantic querying using qualitative relations and bridge the semantic gap between a human user and that of CBIR systems. Three qualitative representations (and several variants) and a corpus of 700 natural scene images have been used to evaluate the effectiveness of image retrieval using this approach.