Keynote Speech : Neural Models for Gestalt Vision and their Applications
게시일: Dec 06, 2017 8:17:44 AM
Mario Köppen studied physics at the Humboldt-University of Berlin and received his master degree in solid state physics in 1991. Afterwards, he worked as researcher at the Central Institute for Cybernetics and Information Processing in Berlin and changed his main research interests to image processing and neural networks. From 1992 to 2006, he was working with the Fraunhofer Institute for Production Systems and Design Technology. He continued his works on the industrial applications of image processing, pattern recognition, and soft computing, esp. evolutionary computation. During this period, he achieved the doctoral degree at the Technical University Berlin with his thesis works: "Development of an intelligent image processing system by using soft computing" with honors. He has published more than 150 peer-reviewed papers in conference proceedings, journals and books and was active in the organization of various conferences as chair or member of the program committee, incl. the WSC on-line conference series on Soft Computing in Industrial Applications, and the HIS conference series on Hybrid Intelligent Systems.
Dr. Mario Köppen
Professor, Graduate School of Creative Informatics, Kyushu Institute of Technology, Japan
Editor-in-Chief, Applied Soft Computing, Elsevier
He is founding member of the World Federation of Soft Computing, and since 2016 Editor-in-Chief of its Elsevier Applied Soft Computing journal. In 2006, he became JSPS fellow at the Kyushu Institute of Technology in Japan, and in 2008 Professor at the Network Design and Research Center (NDRC) and 2013 Professor at the Graduate School of Creative Informatics of the Kyushu Institute of Technology, where he is conducting now research in the fields of soft computing, esp. for multi-objective and relational optimization, digital convergence and human-centered computing.
Abstract of Mario Köppen's Talk
Gestalt and corresponding Gestalt laws of vision are apparent phenomena of visual perception that still lack general understanding, despite of passing more than 100 years after its first mentioning in psychological literature. In this contribution, we want to promote Gestalt as a kind of challenge to the naturally and biologically inspired computation community. Browsing a bulk of existing research literature on the Gestalt theme, with only a few notable exceptions (like the Helmholtz principle), there is not much indication for a comprehensive approach to the understanding of Gestalt, for having explanations about the means for its application, or for advancement in the provision of models reflecting the complex interplay of Gestalt laws in a verifiable manner. Said this, currently Gestalt triggers more questions than answers, and it might slowly become obvious that Gestalt is more than being just a source of inspiration for new algorithms, or for stimulating modifications of existing algorithms. It also gets slowly more clear that the only open issue is not just a lack of "holistic view" in present science, as it is often stated. It seems that any further progress in this regard might require a more rigorous departure from existing computational paradigms and concepts than expected.
In this talk, the state of research on Gestalt in engineering sciences, esp. image processing and pattern analysis, will be critically reviewed, and their strong and weak points will be evaluated. But moreover, new emerging computational paradigms and models will be evaluated according to what they might provide to the understanding of Gestalt. Among these paradigms and models, we can find the Neural Darwinism, which relates evolutionary concepts to the processing of the brain, or the recently proposed Cogency Confabulation, which relates learning with the maximization of a priori probability, and which is accompanied by a novel neural network architecture. Applications of these neural approaches to Gestalt, for example in the subjective evaluation of video quality, will be demonstrated.