Learning Linear Discriminant Projections for Dimensionality Reduction of Image Descriptors

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F08%3A03150834" target="_blank" >RIV/68407700:21230/08:03150834 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Learning Linear Discriminant Projections for Dimensionality Reduction of Image Descriptors

Popis výsledku v původním jazyce

This paper proposes a general method for improving image descriptors using discriminant projections. Two methods based on Linear Discriminant Analysis have been recently introduced to improve matching performance of local descriptors and to reduce theirdimensionality. These methods require large training set with ground truth of accurate point-to-point correspondences which limits their applicability. We demonstrate the theoretical equivalence of these methods and provide a means to derive projection vectors on data without available ground truth. It makes it possible to apply this technique and improve performance of any combination of interest point detectors-descriptors. We conduct an extensive evaluation of the discriminative projection methods invarious application scenarios. The results validate the proposed method in viewpoint invariant matching and category recognition.

Název v anglickém jazyce

Learning Linear Discriminant Projections for Dimensionality Reduction of Image Descriptors

Popis výsledku anglicky

This paper proposes a general method for improving image descriptors using discriminant projections. Two methods based on Linear Discriminant Analysis have been recently introduced to improve matching performance of local descriptors and to reduce theirdimensionality. These methods require large training set with ground truth of accurate point-to-point correspondences which limits their applicability. We demonstrate the theoretical equivalence of these methods and provide a means to derive projection vectors on data without available ground truth. It makes it possible to apply this technique and improve performance of any combination of interest point detectors-descriptors. We conduct an extensive evaluation of the discriminative projection methods invarious application scenarios. The results validate the proposed method in viewpoint invariant matching and category recognition.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2008

Kód důvěrnosti údajů

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

Název statě ve sborníku

BMVC 2008: Proceedings of the 19th British Machine Vision Conference

ISBN

978-1-901725-36-0

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

—

Název nakladatele

British Machine Vision Association

Místo vydání

London

Místo konání akce

Leeds

Datum konání akce

1. 9. 2008

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—