Scale Sensitivity of Textural Features

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F17%3A00471593" target="_blank" >RIV/67985556:_____/17:00471593 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-52277-7_11" target="_blank" >http://dx.doi.org/10.1007/978-3-319-52277-7_11</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-52277-7_11" target="_blank" >10.1007/978-3-319-52277-7_11</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Scale Sensitivity of Textural Features

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Scale Sensitivity of Textural Features

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA14-10911S" target="_blank" >GA14-10911S: Matematické modelování vzhledu povrchových materiálů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: 21st Iberoamerican Congress, CIARP 2016

ISBN

978-3-319-52276-0

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

84-92

Název nakladatele

Springer International Publishing

Místo vydání

Cham

Místo konání akce

Lima

Datum konání akce

8. 11. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000418399200011