Region-based image retrieval with high-level semantics – A Comprehensive Investigation

In this era of information highly accurate data is crucial for all requirements. The current investigation helps in achieving highly accurate image retrieval as close to human interpretation. This paper attempts to provide a comprehensive review and characterize the problem of the semantic gap that is the key problem of region-based image retrieval and the current attempts in high-level semantic-based image retrieval being made to bridge it. In this paper, the latest contributions in research on different methods of image retrieval systems are described and major categories of the state-of-the-art techniques in narrowing down the ‘semantic gap' are presented. Finally, based on existing technologies and the demand from real-world applications, a few promising future research directions are suggested.