Towards Semantic User Query: A Review

Abstract

This paper attempts to discuss the image query mechanisms and user needs for image retrieval. The explosive growth of image data leads to the need of research and development of Image retrieval. Image retrieval researches are moving from keyword, to low level features and to semantic features. Drive towards semantic features is due to the problem of the keywords which can be very subjective and time consuming while low level features cannot always describe high level concepts in the users' mind. This paper also highlights both the already addressed and outstanding issues.

SEVQER: Automatic Semantic Visual Query Builder to Support Intelligent Image Search in Traffic Images

“…The ability to retrieve images based on image semantic content is a clear priority (Eakins et al, 2004) for image database user while embracing the rich image descriptions as opposed to the limited information returned by using short search queries. The fundamental idea of image semantics should be reflected in the searches besides employing image attributes in user search query, whereas user can compare the relevance of image results based on the semantic features that differentiate between the retrieved images (Wang et al, 2015;Westman, 2009).…”