Počet záznamů: 1
BTF Compound Texture Model with Non-Parametric Control Field
- 1.
SYSNO ASEP 0492500 Druh ASEP C - Konferenční příspěvek (mezinárodní konf.) Zařazení RIV D - Článek ve sborníku Název BTF Compound Texture Model with Non-Parametric Control Field Tvůrce(i) Haindl, Michal (UTIA-B) RID, ORCID
Havlíček, Vojtěch (UTIA-B) RIDCelkový počet autorů 2 Zdroj.dok. The 24th International Conference on Pattern Recognition (ICPR 2018). - New York : IEEE, 2018 - ISBN 978-1-5386-3787-6 Rozsah stran s. 1151-1156 Poč.str. 6 s. Forma vydání Tištěná - P Akce The 24th International Conference on Pattern Recognition (ICPR 2018) Datum konání 20.08.2018 - 24.08.2018 Místo konání Beijing Země CN - Čína Typ akce WRD Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova Compound Markov random field model ; Bidirectional texture function ; Texture modeling Vědní obor RIV BD - Teorie informace Obor OECD Automation and control systems Institucionální podpora UTIA-B - RVO:67985556 UT WOS 000455146801028 EID SCOPUS 85059741571 DOI 10.1109/ICPR.2018.8545322 Anotace This paper introduces a novel multidimensional statistical model for realistic modeling, enlargement, editing, and compression of the recent state-of-the-art bidirectional texture function (BTF) textural representation. The presented multispectral compound Markov random field model (CMRF) efficiently fuses a non-parametric random field model with several parametric random fields models. The primary purpose of our modeling texture approach is to reproduce, compress, and enlarge a given measured natural or artificial texture image so that ideally both natural and synthetic texture will be visually indiscernible for any observation or illumination directions. However, the model can be easily applied for BFT material texture editing as well. The CMRF model consists of several parametric sub-models each having different characteristics along with an underlying switching structure model which controls transitions between these submodels. The proposed model uses the non-parametric random field for distributing local texture models in the form of analytically solvable wide-sense BTF Markov representation for single regions among the fields of a mosaic approximated by the random field structure model. The non-parametric control field of BTF-CMRF is reiteratively generated to guarantee identical region-size histograms for all material sub-classes present in the target example texture. The local texture regions (not necessarily continuous) are represented by analytical BTF models modeled by the adaptive 3D causal auto-regressive (3DCAR) random field model which can be analytically estimated as well as synthesized. The visual quality of the resulting complex synthetic textures generally surpasses the outputs of the previously published simpler non-compound BTF-MRF models. The model allows reaching huge compression ratio incomparable with any standard image compression method.
Pracoviště Ústav teorie informace a automatizace Kontakt Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Rok sběru 2019
Počet záznamů: 1