Multi-view facial landmark detector learned by the Structured Output SVM

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00243390" target="_blank" >RIV/68407700:21230/16:00243390 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.sciencedirect.com/science/article/pii/S0262885616300105" target="_blank" >http://www.sciencedirect.com/science/article/pii/S0262885616300105</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.imavis.2016.02.004" target="_blank" >10.1016/j.imavis.2016.02.004</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multi-view facial landmark detector learned by the Structured Output SVM

Popis výsledku v původním jazyce

Abstract We propose a real-time multi-view landmark detector based on Deformable Part Models (DPM). The detector is composed of a mixture of tree based DPMs, each component describing landmark configurations in a specific range of viewing angles. The usage of view specific DPMs allows to capture a large range of poses and to deal with the problem of self-occlusions. Parameters of the detector are learned from annotated examples by the Structured Output Support Vector Machines algorithm. The learning objective is directly related to the performance measure used for detector evaluation. The tree based DPM allows to find a globally optimal landmark configuration by the dynamic programming. We propose a coarse-to-fine search strategy which allows real-time processing by the dynamic programming also on high resolution images. Empirical evaluation on “in the wild” images shows that the proposed detector is competitive with the state-of-the-art methods in terms of speed and accuracy yet it keeps the guarantee of finding a globally optimal estimate in contrast to other methods.

Název v anglickém jazyce

Multi-view facial landmark detector learned by the Structured Output SVM

Popis výsledku anglicky

Abstract We propose a real-time multi-view landmark detector based on Deformable Part Models (DPM). The detector is composed of a mixture of tree based DPMs, each component describing landmark configurations in a specific range of viewing angles. The usage of view specific DPMs allows to capture a large range of poses and to deal with the problem of self-occlusions. Parameters of the detector are learned from annotated examples by the Structured Output Support Vector Machines algorithm. The learning objective is directly related to the performance measure used for detector evaluation. The tree based DPM allows to find a globally optimal landmark configuration by the dynamic programming. We propose a coarse-to-fine search strategy which allows real-time processing by the dynamic programming also on high resolution images. Empirical evaluation on “in the wild” images shows that the proposed detector is competitive with the state-of-the-art methods in terms of speed and accuracy yet it keeps the guarantee of finding a globally optimal estimate in contrast to other methods.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název periodika

Image and Vision Computing

ISSN

0262-8856

e-ISSN

—

Svazek periodika

47

Číslo periodika v rámci svazku

March

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

15

Strana od-do

45-59

Kód UT WoS článku

000377824500006

EID výsledku v databázi Scopus

2-s2.0-84961226711