Colloquium "Retinex based illumination estimation and tone mapping"

Abstract:
Retinex is a model that attempts to model human psycho-visual system and it is used for image enhancement. It has the ability to achieve computational color constancy and to adjust the image brightness and several algorithms have been developed based on this model. One of them is the recently developed Light Random Sprays Retinex, which produces resulting images of high quality. By analyzing and modifying its core it is possible to develop algorithms that achieve high illumination estimation accuracy and perform well when tone mapping high dynamic range images.

CV:
Nikola Banić received his BSc and MSc degree from the Faculty of Electrical Engineering and Computing in Zagreb. He finished the undergraduate and master study program in Computer Science in 2011 and 2013. Currently, he is employed at the Faculty of Electrical Engineering and Computing, University of Zagreb, as a research engineer at the Department of Electronic Systems and Information Processing, where he is pursuing his PhD degree. His research interests are in the area of image processing and machine learning.