Instantaneous mental image search with range queries on multiple region descriptors

The Mental Image Search paradigm allows the user to retrieve images which match the target image s/he has in mind without a starting example. We present a novel approach for this paradigm which enables multiple descriptor range-query, which is necessary to match the more or less precise idea of the user’s mental image. In a simple and intuitive way, sophisticated queries can be formulated on the visual appearance of the mental image components. The query interface maps directly to the region multifeature space using a grid file index. Images are retrieved instantaneously on a large photostock database. Various search scenarios show that the combination of this indexing scheme combined with the query interface is an efficient approach for mental image search.