Color based subject identification for virtual museums, the case of fish

The identification of fish subjects in controlled underwater environments, such as museum, falls into the category of image processing and recognition problems. An interesting aspect of such problems is that they require real time processing and thus effective processing methods must be evolved for the implementation. Although there have been a lot of approaches that solve the identification problem using specialized methods such as contour identification, recognition of distinctive characteristics, besides others, our team at the Multimedia Content lab of TEI Crete has focused on analyzing the color of still images taken from pools in order to rapidly identify subjects.