Most of the existing image retrieval systems take the textual query from the user and utilize the metadata associated with the database images to retrieve the result. However, the...
A combination of several classifiers using global features for the content description of medical images is proposed. Beside well known texture histogram features, downscaled repr...
Abstract. This paper presents novel dissimilarity space specially designed for interactive multimedia retrieval. By providing queries made of positive and negative examples, the go...
: Generic systems for content-based image retrieval (CBIR), such as QBIC [7] cannot be used to solve domain-specific image retrieval problems, as for example, the identification of...
Multiple Instance Learning (MIL) is a special kind of supervised learning problem that has been studied actively in recent years. We propose an approach based on One-Class Support ...