Towards correct and informative evaluation methodology for texture classification under varying viewpoint and illumination

Kód výsledku v IS VaVaI

RIV/68407700:21230/10:00175528 - isvavai.cz

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Towards correct and informative evaluation methodology for texture classification under varying viewpoint and illumination

Popis výsledku v původním jazyce

3D texture classification under varying viewpoint and illumination has been a vivid research topic, and many methods have been developed. It is crucial that these methods be compared using an unbiased evaluation methodology. The most frequently employedmethodologies use images from the Columbia-Utrecht Reflectance and Texture Database. These methodologies construct the training and test sets to be disjoint in the imaging parameters, but do not separate them spatially because they use images of the samesurface patch for both. We perform a series of experiments which show that such practice leads to overestimation of classifier performance and distorts experimental findings. To correct that, we accurately register the images across all imaging conditions and split the surface patches to parts. The training and testing is then done on spatially disjoint parts. We show that such methodology gives a more realistic assessment of classifier performance. The sample annotations for all images

Název v anglickém jazyce

Towards correct and informative evaluation methodology for texture classification under varying viewpoint and illumination

Popis výsledku anglicky

3D texture classification under varying viewpoint and illumination has been a vivid research topic, and many methods have been developed. It is crucial that these methods be compared using an unbiased evaluation methodology. The most frequently employedmethodologies use images from the Columbia-Utrecht Reflectance and Texture Database. These methodologies construct the training and test sets to be disjoint in the imaging parameters, but do not separate them spatially because they use images of the samesurface patch for both. We perform a series of experiments which show that such practice leads to overestimation of classifier performance and distorts experimental findings. To correct that, we accurately register the images across all imaging conditions and split the surface patches to parts. The training and testing is then done on spatially disjoint parts. We show that such methodology gives a more realistic assessment of classifier performance. The sample annotations for all images

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

1M0567: Centrum aplikované kybernetiky

Návaznosti

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

Rok uplatnění

2010

Kód důvěrnosti údajů

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

Název periodika

Computer Vision and Image Understanding

ISSN

1077-3142

e-ISSN

—

Svazek periodika

114

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

11

Strana od-do

—

Kód UT WoS článku

000275985600005

EID výsledku v databázi Scopus

—