Počet záznamů: 1
Scale Sensitivity of Textural Features
- 1.
SYSNO ASEP 0471593 Druh ASEP C - Konferenční příspěvek (mezinárodní konf.) Zařazení RIV D - Článek ve sborníku Název Scale Sensitivity of Textural Features Tvůrce(i) Haindl, Michal (UTIA-B) RID, ORCID
Vácha, Pavel (UTIA-B) RIDCelkový počet autorů 2 Zdroj.dok. Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: 21st Iberoamerican Congress, CIARP 2016. - Cham : Springer International Publishing, 2017 / Beltran-Castanon C. ; Nystrom I. ; Famili F. - ISBN 978-3-319-52276-0 Rozsah stran s. 84-92 Poč.str. 8 s. Forma vydání Tištěná - P Akce CIARP 2016 - 21st Iberoamerican Congress 2016 Datum konání 08.11.2016 - 11.11.2016 Místo konání Lima Země PE - Peru Typ akce WRD Jazyk dok. eng - angličtina Země vyd. DE - Německo Klíč. slova Textural features ; texture scale recognition sensitivity ; surface material recognition ; Markovian illumination invariant features Vědní obor RIV BD - Teorie informace Obor OECD Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) CEP GA14-10911S GA ČR - Grantová agentura ČR Institucionální podpora UTIA-B - RVO:67985556 UT WOS 000418399200011 EID SCOPUS 85013468585 DOI 10.1007/978-3-319-52277-7_11 Anotace Prevailing surface material recognition methods are based on textural features but most of these features are very sensitive to scale variations and the recognition accuracy significantly declines with scale incompatibility between visual material measurements used for learning and unknown materials to be recognized. This effect of mutual incompatibility between training and testing visual material measurements scale on the recognition accuracy is investigated for leading textural features and verified on a wood database, which contains veneers from sixty-six varied European and exotic wood species. The results show that the presented textural features, which are illumination invariants extracted from a generative multispectral Markovian texture representation, outperform the most common alternatives, such as Local Binary Patterns, Gabor features, or histogram-based approaches. Pracoviště Ústav teorie informace a automatizace Kontakt Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Rok sběru 2018
Počet záznamů: 1