Institute of Information Theory and Automation

You are here

Prof. Ing. Jan Flusser, DrSc.

Position: 
Vice director for research
Mail: 
Room: 
Fax: 
286890378
Phone: 
266052422
266052357
Research interests: 
Image processing, pattern recognition, artificial intelligence
Publications ÚTIA: 

Education & Affiliation

Jan Flusser was born on the 30th April 1962 in Prague, Czech Republic. He received the M.Sc. degree in mathematical engineering from the Faculty of Nuclear Science and Physical Engineering, Czech Technical University, Prague, in 1985, the Ph.D degree in computer science from the Czechoslovak Academy of Sciences in 1990, and the DrSc. degree in technical cybernetics from the Czech Technical University in 2001. Since 1985 he has been with the Institute of Information Theory and Automation. In 1995-2007 he was holding the position of a head of Department of Image Processing and the position of the Director of the Institute from 05/01/2007 to 04/30/2017. Currently he is the Research Director and the Chair of the Board of the Institute.

Research

Jan Flusser's research interest is on the field of invariant-based pattern recognition and image fusion. His main areas are moments and moment invariants, image registration, multichannel blind deconvolution, and super-resolution imaging. He has authored and coauthored more than 200 research publications in these areas, including the books Moments and Moment Invariants in Pattern Recognition (Wiley, 2009), 2D and 3D Image Analysis by Moments (Wiley, 2016), 100 papers in prestigious journals and over 20 tutorials at international conferences (ICIP'05, ICIP'07, EUSIPCO'07, CVPR'08, FUSION'08, SPPRA'09,  ICIP'09, SPPRA'10, CGIM'10, AIA'14, CI'15,  ICPR'16,  ICIP'18, and ICASSP'19) and invited/keynote talks (ICCS'06, COMPSTAT'06, WIO'06, DICTA'07, CGIM'08, and SCIA'09). His publications have received almost 20 000 citations. Jan Flusser has been involved in numerous research projects (both Czech and international ones) and in successful applications in computer vision, remote sensing, medicine, and astronomy. His work (with co-authors) on image restoration in astronomy was awarded by the Award of the Chairman of the Czech Science Foundation (GA CR) in 2007. In the same year, his team won the Prize of the Academy of Sciences of the Czech Republic for the contribution to image fusion theory. In 2010, he was awarded (jointly with B. Zitova) by the prestigious SCOPUS 1000 Award presented by Elsevier. He received the Felber Medal of the Czech Technical University in 2015 and the Academic Premium awarded by the Czech Academy of Sciences in 2017. More about the Jan Flusser's research can be found here.

Teaching & Supervising

Since 1991 he has been also affiliated with the Faculty of Mathematics and Physics, Charles University (MFF UK), Prague and with the Faculty of Nuclear Science and Physical Engineering, Czech Technical University (FJFI CVUT), Prague (habilitation in Computer Science at MFF UK in 1998, full professorship in Applied Mathematics at FJFI CVUT in 2004), where he gives undergraduate and graduate courses on Digital Image Processing, Pattern Recognition, Machine Learning, and Moment invariants and wavelets. He has been a supervisor of several Ph.D Theses (list) and Master diploma Theses (list). He is also a member of several committees for state examinations, for Ph.D defences in Computer Science, and the Chair of the committee for  DSc. defences in Computer Science and Cybernetics. He was the founder and the first  Chairman of the Board of Ph.D study in Computer Graphics and Image Analysis at MFF UK (2012-2016). He is a member of the Board of Ph.D study in Mathematical Engineering at FJFI CVUT, and a member of the Board of Ph.D study in Artificial Intelligence and Biocybernetics at FEL CVUT. Jan Flusser acts also as an external supervisor of Ph.D students in Computer Science at the Unversity of Technology Malaysia, Johor Bahru.

Organizing & Others

Jan Flusser has been a member of numerous program and organizing committees at international conferences and personally organized and chaired two special sessions (COMPSTAT'06 and CGIM'08). He is a member of the Editorial Board of the journal Kybernetika, a member of the Czech Committee for Mathematics (IMU), a member of the Scientific Board of the University of West Bohemia, a member of the Scientific Board of the Faculty of Mathematics and Physics, Charles University (2012-2016); a member of the Scientific Board of the Faculty of Management, the University of Economics, a member of the Scientific Board of the Faculty of Informatics, the Masaryk University Brno (2010-2014), a member of the Scientific Board of the Faculty of Science of the UJEP in Ústí nad Labem,  a member of the Ethical Committee of the Czech Academy, and a Senior Member of the IEEE.

2023-02-15 21:10

Person detail

Duration: 2024 - 2026
Current convolutional networks work with inefficient pixel-wise image representation, which does not provide almost any invariance. This leads to using very large training sets and massive augmentation.
Duration: 2021 - 2024
The project aims at developing a conceptually novel approach to inverse problems by proposing a unified theory of invariants to integral transformations using projection operators, and applying it to image restoration and classification problems in biomedical imaging and robotics.
Duration: 2018 - 2021
The proposal falls into the area of computer image analysis and pattern recognition. It is focused on special type of data - multidimensional vector and tensor fields. Vector fields may describe particle velocity, optical/motion flow, image gradient, deformation/condutivity/diffusion tensors, and other phenomena.
Duration: 2018 - 2023
Duration: 2015 - 2017
The project falls into the area of image analysis and object recognition. We mainly focus on two important connected areas: object description by invariant features and image fusion. The theoretical concept is based on the formulation of all tasks as optimization problems and looking for proper cost functions and algorithms for their maximization.
Duration: 2014 - 2017
The goal of the project is to develop a sophisticated software for videokymography (VKG) which will enable automatic evaluation of medical videokymographic recordings of vibrating vocal folds and arrive at correct medical diagnosis. Further goal is to develop a certified method of VKG evaluation to be used in clinical practice.

Current

Graduates

Ing. Václav Košík
RNDr. Matěj Lébl
Dr. Sajad Farokhi Ph.D.
RNDr. Radim Halíř Ph.D.
Ing. Ondřej Horáček Ph.D.
RNDr. Cyril Höschl Ph.D.
Ing. Jan Kamenický Ph.D.
Ing. Jitka Kostková Ph.D.
Mgr. Filip Krolupper Ph.D.
Mgr. Jiří Sedlář Ph.D.
RNDr. Michal Šorel Ph.D.
Doc. Ing. Filip Šroubek Ph.D. DSc.
RNDr. Aleš Zita Ph.D.
Doc. RNDr. Barbara Zitová Ph.D.
Matematicko-fyzikální fakulta UK
Fakulta jaderná a fyzikálně-inženýrská ČVUT
Fakulta jaderná a fyzikálně-inženýrská ČVUT