Congratulations to Lukáš Krasula on successful Ph.D. thesis defense!

Lukáš Krasula successfully defended his Ph.D. thesis titled Quality Assessment of Post-Processed Images at the Czech Technical University in Prague on January 20, 2017. Lukáš was a double degree Ph.D. student at Czech Technical University in Prague and Université de Nantes, France. He will receive his Ph.D. title from both universities.

Patrick Le Callet, Frédéric Dufaux, Dragan Kukolj, Lukáš Krasula, Karel Fliegel, Miloš Klíma, Jiří Myslík, Tomáš Kratochvíl, Jiří Masopust, Nicolas Normand

Supervisors: Miloš Klíma (Czech Technical University in Prague), Patrick Le Callet (Université de Nantes, France), and Karel Fliegel (Czech Technical University in Prague)

Reviewers: Frédéric Dufaux (Directeur de Recherche CNRS, France, Editor-in-Chief, Signal Processing: Image Communication), Dragan Kukolj (University of Novi Sad, Serbia), and Jiří Masopust (University of West Bohemia).

Quality Assessment of Post-Processed Images

Abstract: The vast majority of the work done in the field of quality assessment during last two decades has been dedicated to the quantification of the distortion caused by the processing of an image. The original image was, therefore, always considered to be of the best possible quality. In this kind of scenario, the notion of quality can be expressed as the fidelity of the processed version to the reference. However, some post-processing algorithms enable to adjust aesthetic properties of an image in order to enhance the perceived quality. In such cases, the best possible quality image is not available and the classical fidelity approach is no longer applicable. The goal of this thesis is to revise the quality assessment methodologies to cope with the challenges brought by the post-processing into the quality evaluation. The post-processing algorithms, relevant to the topic of this thesis, come from two groups – image enhancement, represented by image sharpening, and dynamic range compression (also known as tone-mapping) techniques. Both subjective and objective quality assessment methodologies applicable in these areas are studied and the suitable solutions, outperforming the state-of-the-art methods, are proposed. Moreover, a novel methodology for evaluating the performance of objective quality metrics, overcoming the shortcomings of the currently available methods, is presented.

Selected publications:

[TIP2016] L. Krasula, P. Le Callet, K. Fliegel, M. Klíma. Quality Assessment of Sharpened Images: Challenges, Methodology, and Objective Metrics, IEEE Transactions on Image Processing, (accepted for publication).

[JSTSP2016] L. Krasula, M. Narwaria, K. Fliegel, and P. Le Callet. Preference of experience in image tone-mapping: Dataset and framework for objective measures comparison. IEEE Journal on Selected Topics in Signal Processing, (accepted for publication).

[QoMEX2016] L. Krasula, K. Fliegel, P. Le Callet, M. Klíma. On the accuracy of objective image and video quality models: New methodology for performance evaluation, International Conference on Quality of Multimedia Experience (QoMEX), 2016.

[QoMEX2015] L. Krasula, M. Narwaria, K. Fliegel, and P. Le Callet. Influence of HDR reference on observers preference in tone-mapped images evaluation. International Workshop on Quality of Multimedia Experience (QoMEX), 2015.

[SPIE2015] L. Krasula, M. Narwaria, K. Fliegel, and P. Le Callet. Rendering of HDR content on LDR displays: An objective approach. SPIE Applications of Digital Image Processing XXXVIII, 2015.

[SPIE2014] L. Krasula, M. Narwaria, and P. Le Callet. An automated approach for tone mapping operator parameter adjustment in security applications. SPIE 9138, Optics, Photonics, and Digital Technologies for Multimedia Applications III, 2014.

Complete list of Lukáš Krasula’s publications.

Dean’s award: Lukáš Krasula honored with dean’s award for a prestigious dissertation on March 8, 2017. Read more…

Lukáš Krasula and Prof. Pavel Ripka (Dean of the Faculty of Electrical Engineering, Czech Technical University in Prague)


Joseph Fourier Prize for Computer Sciences 2017: 2nd place for Lukáš Krasula in Joseph Fourier Prize for Computer Sciences 2017 on the topic Design and Evaluation of Automatic Image and Video Quality Assessment Algorithms. The official awarding took place on June 16, 2017, at a reception in the Buquoy Palace, the seat of the French Embassy, in the presence of His Excellency, the Ambassador of France to the Czech Republic. The awards were given to the laureates by Professor Jean-Marie Lehn, the Nobel Laureate in Chemistry for 1987. Pavel Bělobrádek, Deputy Prime Minister and Minister of Science and Research, and Karel Janeček, mathematician, entrepreneur, anti-corruption campaigner, and philanthropist, also gave a speech at the ceremony.

Czech Television (CT 24) – Czech students received prizes for their excellent scientific work. They were handed over by nobelist Jean-Marie Lehn. (newsreel in Czech)

2nd place in Joseph Fourier Prize for Computer Sciences 2017

Joseph Fourier Prize for Computer Sciences 2017 (Jaroslav Vojtěch – Head of Big Data & Cyber Security, Atos Czech Republic; 1st Prize – Jan Zapletal – Technical University of Ostrava; 2nd Prize – Lukáš Krasula – Czech Technical University in Prague – represented by Karel Fliegel – thesis co-supervisor; 3rd Prize – Jakub Sochor – Brno University of Technology; Martin Palkovič – Managing Director – IT4Innovations national supercomputing center)

Laureates of various scientific prizes awarded by the French Embassy with Nobelist Professor Jean-Marie Lehn.