Katsaggelos is Keynote Speaker at 2015 International Conference on Systems, Signals and Image Processing

His talk, titled, "Learning for Future Video" was delivered at City University London on September 10-12.

The 22nd International Conference on Systems, Signals and Image Processing

Prof. Aggelos K. Katsaggelos delivered a keynote talk, titled, "Learning for Future Video" at the The 22nd International Conference on Systems, Signals and Image Processing (IWSSIP 2015), in London, UK at City University London on September 10-12, 2015.

Talk Abstract: Learning has made it possible to unleash the power of data. We have moved away from the detailed modeling of a system or a phenomenon of interest thanks to the abundance of data as well as the huge improvements in processing power. With approaches like dictionary learning we can discover linear relationships between the input and output. On the other hand, recent advancements in deep learning have made it possible to discover non-linear relationships. As one of the examples in this talk we discuss the application of dictionary and deep learning to the video super-resolution problem. We describe a multiple-frame algorithm based on dictionary learning and motion estimation. We further describe the use of a convolutional neural network that is trained on both the spatial and temporal dimensions of videos to enhance their resolution. We demonstrate experimentally the effectiveness of these approaches. We finally discuss future research directions on the topic of learning.

IWSSIP is an international conference on theoretical, experimental and applied signal/image processing techniques.

IWSSIP brings together researchers and developers from both academia and industry to report on the latest scientific and theoretical advances to discuss and debate major issues and to demonstrate state-of-the-art systems.

The program included keynote talks presented by eminent experts in the field and presentations of peer reviewed contributed papers. Several special sessions will be organized during the Conference. Authors are encouraged to submit their papers to these special sessions.

IWSSIP was founded by Professor Kalman Fazekas from the Budapest University of Technology and Economics, Budapest, Hungary, who initiated it in June 1994 as a scientific event meant to stir the research in theory, methodology, systems and applications of signal and image processing, and to attract and stimulate young researchers.