Keynote Speakers, Keynotes and Tutorials

We regret to inform that due to circumstances outside his control, Prof. Oscar Corcho from the Universidad Politécnica de Madrid, has had to cancel his keynote and tutorial. We apologise for any inconvenience.

Keynote Speakers

Prof Aggelos Katsaggelos Northwestern University (US)

Aggelos K. Katsaggelos received the Diploma degree in electrical and mechanical engineering from the Aristotelian University of Thessaloniki, Thessaloniki, Greece, in 1979 and the M.S. and Ph.D. degrees both in electrical engineering from the Georgia Institute of Technology, Atlanta, Georgia, in 1981 and 1985, respectively. In 1985 he joined the Department of Electrical Engineering and Computer Science at Northwestern University, Evanston, IL, where he is currently professor, holder of the AT&T Chair (previously holder of the Ameritech Chair). He is also the Director of the Motorola Center for Seamless Communications, an Academic Affiliate Staff, Department of Medicine, at NorthShore University HealthCare System, an affiliated faculty at the Department of Linguistics, Northwestern University, and an appointee at the Argonne National Laboratory. During the 1986-1987 academic year he was an assistant professor at Polytechnic University, Department of Electrical Engineering and Computer Science, Brooklyn, NY. His current research interests include multimedia signal processing (e.g. image and video recovery and compression, audio-visual speech and speaker recognition, indexing and retrieval), multimedia communications, computer vision, pattern recognition, and DNA signal processing. He has published extensively in these areas. He is the editor of Digital Image Restoration (Springer-Verlag 1991), co-author of Rate-Distortion Based Video Compression (Kluwer 1997), co-editor of Recovery Techniques for Image and Video Compression and Transmission, (Kluwer 1998), and co-author of Super-Resolution of Images and Video (Morgan & Claypool Publishers 2007) and Joint Source-Channel Video Transmission (Morgan & Claypool Publishers 2007). Prof. Katsaggelos has served in the IEEE and other professional Societies in many capacities. He is currently a member of the IEEE Technical Committee on Visual Signal Processing and Communications, and the Editorial Boards of Academic Press, Marcel Dekker: Signal Processing Series, the International Journal on Image and Video Processing, and Advances in Multimedia. He has served as editor-in-chief of the IEEE Signal Processing Magazine (1997-2002), a member of the Publication Boards of the IEEE Signal Processing Society, the IEEE TAB Magazine Committee, an Associate editor for the IEEE Transactions on Signal Processing (1990-1992), an area editor for the journal Graphical Models and Image Processing (1992-1995), a member of the Steering Committees of the IEEE Transactions on Image Processing (1992-1997) and the IEEE Transactions on Medical Imaging (1990-1999), a member of the IEEE Technical Committee on Image and Multi-Dimensional Signal Processing (1992-1998), a member of the Board of Governors of the IEEE Signal Processing Society (1999-2001), a member of the IEEE Technical Committees on Multimedia Signal Processing and Image and Multidimensional Signal Processing, a member of the Publication Board of the IEEE Proceedings (2003-2007), and a member of the Editorial Boards of Applied Signal Processing and Computer Journal. He has served as the General Chairman of the 1994 Visual Communications and Image Processing Conference (Chicago, IL) and as technical program co-chair of the 1998 IEEE International Conference on Image Processing (Chicago, IL). Dr. Katsaggelos is a Fellow of the IEEE (1998) and SPIE (2009), the co-inventor of seventeen international patents, the recipient of the IEEE Third Millennium Medal (2000), the IEEE Signal Processing Society Meritorious Service Award (2001), the IEEE Signal Processing Society Technical Achievement Award (2010), and a co-recipient of an IEEE Signal Processing Society Best Paper Award (2001), an IEEE ICME Best Paper Award (2006), an IEEE ICIP Best Paper Award (2007), and an ISPA Best Paper Award (2009). He was a Distinguished Lecturer of the IEEE Signal Processing Society (2007-08).

Prof Ebroul Izquierdo Queen Mary University of London (UK)

Ebroul Izquierdo, PhD, MSc, CEng, FIET, SMIEEE, MBMVA, is Chair of Multimedia and Computer Vision and head of the Multimedia and Vision Group in the school of Electronic Engineering and Computer Science at Queen Mary, University of London. For his thesis on the numerical approximation of algebraic-differential equations, he received the Dr. Rerum Naturalium (PhD) from the Humboldt University, Berlin, Germany. He has been a senior researcher at the Heinrich-Hertz Institute for Communication Technology (HHI), Berlin, Germany, and the Department of Electronic Systems Engineering of the University of Essex. Prof. Izquierdo is a Chartered Engineer, a Fellow member of the The Institution of Engineering and Technology (IET), a senior member of the IEEE, a member of the British Machine Vision Association, past chairman of the IET professional network on Information Engineering, member of the Visual Signal Processing and Communication Technical Committee of the IEEE Circuits and Systems Society and member of the Multimedia Signal Processing technical committee of the IEEE. Prof. Izquierdo is or has been associated and guest editor of several relevant journals in the field including the IEEE Transactions on Circuits and Systems for Video Technology, the IEEE Transactions on Multimedia, the EURASIP Journal on Image and Video processing, the Elsevier journal Signal Processing: Image Communication, The EURASIP Journal on Applied Signal Processing, the IEE Proceedigs on Vision, Image & Signal Processing, the Journal of Multimedia Tools and Applications and the Journal of Multimedia. He has been member of the organizing committee of several conferences and workshops in the field and has chaired special sessions and workshops in ICIP, ICASSP and ISCAS. He has been the general chair of the European Workshop on Image Analysis for Multimedia Interactive Services, London 2003 and Seoul 2006, the European Workshop for the integration of Knowledge, Semantics and Content, London 2004 and 2005, the Mobile Multimedia Communications Conference MobiMedia, Algero2006, the International Conference on Content Based Multimedia Indexing, London 2008 and the IET Conference on Visual Information Engineering, Xian 2008.

Prof Emanuel Trucco Universty of Dundee (Scotland)

Emanuel Trucco FSRA, obtained his MEng (1984) and PhD (1990) degrees from the University of Genoa, Italy, both in electronic engineering. He has been active in theoretical and applied computer vision research since 1984 at the Universities of Genoa, Edinburgh, Heriot Watt, Dundee, and at the Joint Research Centre of the European Communities at Ispra, Italy. He is currently the Professor of Computational Vision in the School of Computing, University of Dundee, UK, and an Honorary Clinical Researcher at Ninewells NHS and University Hopspital, Dundee. His research has spanned applications of computer vision to manufacturing, subsea robotics, immersive videoconferencing, and medical image analysis. His current interests are in medical image processing. He leads imaging research in the EU CODIR project (robotic hydrocolonoscopy), and co-ordinates with Tom MacGillivray (CRIC, Univ of Edinburgh, UK) the VAMPIRE initiative (Vascular Assessent and Measurement Platform for Images of the REtina), an international collaboration of 10 image processing and clinical centres developing a software suit for efficient automatic and semi-automatic analysis of retinal images. He has recently co-ordinated a group of 12 international research centres in Europe, Asia, Australia and America to publish a large-consensus paper of issues and recommendations for the validation of retinal image analysis algorithms, appearing in IOVS in 2013. Dr Trucco serves regularly on the technical and organising committees of the major international conferences in computer vision, and has served as associate editor for Pattern Analysis and Applications and the IEEE Transactions on Systems, Man and Cybernetics, and as Editor-in-Chief of the IEE Proceedings on Vision, Image and Signal Processing. He has been invited as a speaker and lecturers at various conferences and schools, including the British Machine Vision Conference and the IEEE Conference on Biosignals and Biorobotics, and at various universities, including the National Univ of Singapore, the Universities of Girona (Spain), Genova, Verona, Palermo and Udine (Italy). He has published more than 140 refereed papers and co-authored two textbooks, one of which (with Alessandro Verri) has become an international standard (2061 citations, Google Scholar March 2012).

Prof Panos Liatsis City University London (UK)

Panos Liatsis graduated with the Diploma degree in Electrical Engineering from the Department of Electrical and Computer Engineering at the Democritus University of Thrace, Greece. He received the PhD degree in Electrical Engineering and Electronics from the Control Systems Centre at the University of Manchester (UMIST). He joined the School of Engineering and Mathematical Sciences at City University London in 2003, where he is now Professor of Image Processing and Head of the Department of Electrical and Electronic Engineering. Panos’ research interests include pattern recognition, image processing and computer vision, neural and evolutionary systems with applications in biomedical image and signal processing, intelligent transportation systems and cultural heritage. He has published around 160 research contributions in high-impact factor journals, books and international conference proceedings.

Keynote Talks

Prof Aggelos Katsaggelos: Advances in Sparsity-Based Image Processing
Prof Emanuel Trucco: Towards usable computer-assisted retinal image analysis: algorithms, promises, realities
The eye is the only opening in the human body through which a significant, complex part of the blood circulation system (the retinal vasculature) is visible without complex instruments. Morphological changes in the retinal vasculature have been associated with systemic conditions, most importantly diabetes and stroke, making retinal blood vessels an important and easily accessible source of biomarkers for various conditions. This talk will discuss the rationale and promise of computer-assisted retinal image analysis and its potential for screening programmes, including a brief overview of current image analysis techniques. The international initiative, VAMPIRE (Vessel Assessment and Measurement Platform for Images of the REtina), led by Trucco's group in collaboration with the Univ of Edinburgh, will also be presented.
Prof Ebroul Izquierdo: Automated face recognition and efficient data mining in forensic applications
Nowadays, society faces serious problems derived from heightened vandalism and more critically the fatal consequences of terrorist activities. The vast amounts of video surveillance data generated from many different and diverse security systems require efficient automatic tools to ease the task of human analysts. These tools should be incorporated into unified systems to automatically handle the laborious and tedious tasks of searching for evidence in vast forensic databases; hence, alleviating the workload of forensic investigators. Advances in computer vision are providing key tools to solve or at least lighten underlying problems. Here, computer aided recognition of people and their most fundamental characteristics or traits play a crucial role. Face recognition is indeed one of the main biometric tools used for automated enhancement of security and person identification in critical events. However, mining the vast amounts of data for person recognition achieving suitable levels of accuracy is still an open problem.

In this talk several important biometric tools and data mining techniques for automated person recognition in security applications will be outlined. As key example, recent advances in face recognition technology will be presented and discussed. The talk will also refer to important mathematical and statistical tools used to achieve highly accurate face recognition, as well as, the advantages and disadvantages of available algorithmic solutions. The state-of-the art and cutting edge achievements in the field will be illustrated. Related data mining techniques will be presented. Finally, still open questions in the area will be discussed and key related international R&D projects will be introduced.

Prof Panos Liatsis: A Coronary Computed Tomography System for Virtual Fractional Flow Reserve
Artherosclerosis is a condition where plaques become clogged up in the medium and large arteries of the heart, which could lead to severe consequences, such as heart attack and stroke. Fractional flow reserve (FFR), a technique which measures the pressure differences between a stenotic artery and the normal segment proximal to the lesion, is considered to be the gold standard for the diagnosis of myocardial ischemia in clinical practice. However, as it is an invasive procedure, it carries a certain amount of risk in terms of morbidity and mortality.
Despite the significant volume of past and on-going CT research, characterisation of local geometrical information in the vicinity of a vessel bifurcation remains a changeling task, due to the irregular local geometries of the bifurcation. The first objective of this presentation is to introduce an automated algorithm for simultaneous determination of centrelines and reference surfaces in coronary bifurcations, based on the concept of deformable tube registration. This works directly on the mesh domain, which alleviates the requirement for image upsampling, and contrary to conventional circular cross sectional tube models, the tubular cross sections are estimated based on partial information of the vessel surface to be fitted. A weighted directional distance metric is employed to measure the goodness of the fit between the tube and the vessel of interest in the energy calculation, which facilitates tube registration at the desired location of the bifurcation.
Next, the proposition of being able to measure non-invasively fractional flow reserve by coronary computed tomography angiography (FFRct) is considered. The second objective of this work presentation is to provide an overview, supported by preliminary results, of a) the fundamental engineering principles behind Computational Fluid Dynamics modelling of coronary arterial blood flow, b) the difficulties faced from an engineering perspective in developing a truly representative model and c) the challenges this technology is likely to face as it attempts to enter the clinical domain.

Tutorial Sessions

Prof Emanuel Trucco: Introduction to multi-camera articulated action understanding
This short course will introduce the problems and key techniques for the analysis of human articulated motion, mainly from multiple-camera videos. Topics include introductory units on motion capture, body models, motion tracking, action modelling, action recognition and dimensionality reduction. The material privileges breadth over depth and provides numerous pointers to further readings.
Prof Aggelos Katsaggelos: Sparse and Redundant Representations: Theory and Applications
Prof Ebroul Izquierdo: Mathematical tools in Image and Video Processing
This tutorial is designed for postgraduate students of mathematics, physics or engineering. Its main objective is to provide a good understanding of the most relevant image and video processing advanced mathematical tools including selected linear algebra techniques, fourier Analysis, partial differential equations, graph theory and multi-objective optimization with direct application in image and video processing. In a concise manner, advanced mathematical tools underpinning technology related to image and video processing will be presented.