RNDr. Michal Šorel, Ph.D.

Michal Šorel

Position: research fellow
Phone: +420 26605 2069
Room: 48
Address: ÚTIA AV ČR, Pod Vodárenskou věží 4, CZ-182 08, Praha 8, Czech Republic
Research interests: space-variant restoration, image stabilization, deblurring, noise reduction, super-resolution, blind deconvolution, image registration, machine learning, digital image processing and pattern recognition in general
Publications: list


Michal Šorel received the M.Sc. and Ph.D. degrees in computer science from the Charles University in Prague, Czech Republic, in 1999 and 2007, respectively. From 2012 to 2013 he worked on a range of topics related to computer vision at the Heriot-Watt University in Edinburgh, Scotland and the University of Bern, Switzerland. Currently he is a research fellow in the Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic. He is a member of the IEEE. Michal Šorel has been a reviewer for the IEEE Transactions on Image Processing, IEEE Transactions on Signal Processing, IEEE Transactions on Pattern Analysis and Machine Intelligence, and several other journals and conferences.

He organizes the Spring and Winter Schools of Image Processing, popular meeting points of students from several czech institutions involved in image processing research (see Seminars). He is also involved in the organization of the Prague computer science seminar and the Friday seminars of the Department of Image Processing.

Currently supervised master theses

  • Dominik Dušek, Segmentation and classification of LIDAR data
  • Matěj Straka, Object recognition by deep neural networks
  • David Honzátko, Generative neural networks in image reconstruction