Texture fidelity criterion

0463638 - ÚTIA 2017 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Kudělka, Miloš - Haindl, Michal
Texture fidelity criterion.
Proceedings of the 2016 IEEE International Conference on Image Processing. Piscataway: IEEE, 2016. ISBN 978-1-4673-9961-6. E-ISSN 2381-8549.
[2016 IEEE International Conference on Image Processing (ICIP). Phoenix, AZ (US), 25.09.2016-28.09.2016]
Grant CEP: GA ČR(CZ) GA14-10911S
Institucionální podpora: RVO:67985556
Klíčová slova: Image texture * texture fidelity * visual quality criterion * Markovian texture model
Kód oboru RIV: BD - Teorie informace
http://library.utia.cas.cz/separaty/2016/RO/haindl-0463638.pdf

Visual texture fidelity evaluation is important but still unsolved problem. Evaluation of how well various texture models conform with human visual perception of their original measured pattern is required not only for assessing the visual dissimilarities between a model output and the original measured texture, but also for optimal settings of model parameters, for fair comparison of distinct models, or visual scene understanding. We propose a novel texture fidelity criterion based on the fully multi-spectral generative underlying Markovian texture model, which correlates well with human texture quality ranking verified on the texture fidelity benchmark.
Trvalý link: http://hdl.handle.net/11104/0263673