COSIS: A Content-Oriented Shoeprint Identification System
M. Meharga, Corinne Plazanet, Stefano Spaccapietra · 1999
COSIS is a content-based image retrieval system designed for the shoeprint identification. It consists of a matching-based query tool, an attribute-based query tool and an icon-based browser. The matching-based tool considers the complete and partial shoeprints as query images. The completeshoeprint query tool is fully-automatic whereas the partial-shoeprint one is user-driven. The development of the matching-based query tool is inspired from the template-matching approach largely used in pattern recognition. This paper presents COSIS by focusing, in particular, on its main component: the Matching-based Query Tool. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.