Although much progress has been made, current lowlevel based visual information retrieval technology does not allow users to formulate queries through high-level semantics. More a...
In this paper, an image retrieval methodology suited for search in large collections of heterogeneous images is presented. The proposed approach employs a fully unsupervised segme...
Vasileios Mezaris, Ioannis Kompatsiaris, Michael G...
One of the major problems in CBIR is the so-called `semantic gap': the difference between low-level features, extracted from images, and the high-level `information need'...
Walter ten Brinke, David McG. Squire, John Bigelow
Human superiority over computers in identifying natural objects like clouds, water, grass etc. comes from two capabilities: the capability to maintain a growing knowledge base per...
Search engines are among the most useful Internet applications. There exist several media types on the Web and, given the particularities of each of them, adapted search solutions...