Ontology based Image Retrieval Framework Using Qualitative Semantic Image Descriptions

This research proposes an ontology based image retrieval framework from a corpus of natural scene images by imparting human cognition in the retrieval process. The proposed architecture addresses the issues of keyword based image retrieval and content-based image retrieval through the use of qualitative spatial representations over semantic image annotations. Domain ontology has been developed to model qualitative semantic image descriptions and retrieval, thereafter can be accomplished either using a natural language description of an image containing semantic concepts and spatial relations, or in a query by example fashion. A psychophysical evaluation has also been carried out to evaluate the effectiveness of our approach and results of different experiments are quite promising in terms of retrieval accuracy and relevance of retrieved images.