Thesis (Selection of subject)Thesis (Selection of subject)(version: 390)
Thesis details
   Login via CAS
Evolučné prístupy k reprezentácii a generovaniu obrázkov
Thesis title in thesis language (Slovak): Evolučné prístupy k reprezentácii a generovaniu obrázkov
Thesis title in Czech: Evoluční přístupy pro reprezentaci a generování obrázků
Thesis title in English: Evolutionary approaches to image representation and generation
Key words: genetické algoritmy, evoluční strategie, evoluční umění
English key words: genetic algorithms, evolutionary strategies, evolutionary art
Academic year of topic announcement: 2020/2021
Thesis type: Bachelor's thesis
Thesis language: slovenština
Department: Department of Theoretical Computer Science and Mathematical Logic (32-KTIML)
Supervisor: Mgr. Roman Neruda, CSc.
Author: hidden - assigned and confirmed by the Study Dept.
Date of registration: 21.07.2020
Date of assignment: 21.07.2020
Confirmed by Study dept. on: 22.07.2020
Date and time of defence: 14.09.2020 09:00
Date of electronic submission:30.07.2020
Date of submission of printed version:31.07.2020
Date of proceeded defence: 14.09.2020
Opponents: Petra Vidnerová
 
 
 
Guidelines
Cílem práce je prozkoumat různé varianty evolučních algoritmů v oblasti reprezentace a generování obrazových dat. Student ověří možnosti reprezentace obrazu a využití evolučních technik pro jejich optimalizaci. Předpokládá se implementace algoritmů jako jsou genetický algoritmus a varianty evolučních strategií. Implementované algoritmy budou srovnány pomocí experimentů na reálných obrazových datech.
References
[1] Koza, John R. (1996). Genetic programming : on the programming of computers by means of natural selection (6. print ed.). Cambridge, Mass.: MIT Press. ISBN 0-262-11170-5.

[2] Eiben, Agoston E., and James E. Smith. Introduction to evolutionary computing. Springer,, 2003.

[3] Peter Bentley. Evolutionary design by computers. Morgan Kaufmann, 1999. ISBN 1-55860-605-X.

[4] Matthew Lewis. "Evolutionary Visual Art and Design". The Art of Artificial Evolution, pp. 3-37. Springer 2008. ISBN: 978-3-540-72876-4. DOI: 10.1007/978-3-540-72877-1_1

[5] Stephen Todd and William Latham. Evolutionary art and computers. Academic Press, Inc., 1994. ISBN 9780124371859.

[6] Hansen, N. a Ostermeier, A. (2001). Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation, 9(2), 159–195. doi: 10.1162/106365601750190398.
Preliminary scope of work
The goal of this work is to explore different variants of evolutionary algorithms in the area of image data representation and generation. The student will revise possibilities of image representation and the use of evolutionary techniques for their optimization. Implemented algorithms will include genetic algorithm as well as versions of evolutionary strategies. Implemented algorithms will be compared by means of experiments on real image data.
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html