Skip to Main Content
In this paper we present our experience in retrieving images from a database by applying the combination of content and pixel-based methods. We consider two typical databases: One of them contains images visually similar to the input and the other one doesnpsilat. We investigate how to choose the value of the threshold in both cases. The Oracle database and the IBM QBIC are used for investigation purposes.
Date of Conference: 25-28 June 2008