Prof. Peter Stanchev
Kettering University, Flint, Michigan, USA
By Prof. Peter Stanchev, Kettering University, Flint, Michigan, USA.
Different multimedia descriptors, such as local features, bag of words, Fisher vector, Vector of local aggregated descriptors, and MPEG-7 will be presented. Approaches for extracting higher-level visual features for art paintings and for extending the learning set of a classification algorithm with additional metadata will be discussed. We will show tools for extracting specific feature combinations, which represent different sides of artists’ styles, periods, and movements. Video streams descriptors will be also presented. An efficient video stream filtering solution that is based on MPEG-7 descriptors will be shown. It uses a novel approach that we call Pivoted Streams. The solution exploits the properties of metric spaces in order to reduce the computational load of the filtering receiver.
Biography
Dr. Peter Stanchev is currently Professor at Kettering University, Flint, Michigan, USA and Professor and Chair of a department at the Institute of Mathematics and Informatics, Bulgarian Academy of Sciences, Sofia, Bulgaria. He has published 2 books, more than 200 chapters in monographs, journal, and conference peer-reviewed papers, more than 200 conference papers and seminars, and has had more than 1500 citations, h-index – 33, impact factor – 77.03. His research interests are in the field of multimedia systems, database systems, multimedia semantics, education and medical systems. Serving also on many database and multimedia conference program committees, he is currently editor-in-chief and member of the editorial boards of several journals. He is the Bulgarian representative in the EU OpenAIRE2020 project.