Local binary pattern based face recognition with automatically detected fiducial points

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F16%3A43928663" target="_blank" >RIV/49777513:23520/16:43928663 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.3233/ICA-150506" target="_blank" >http://dx.doi.org/10.3233/ICA-150506</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3233/ICA-150506" target="_blank" >10.3233/ICA-150506</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Local binary pattern based face recognition with automatically detected fiducial points

Popis výsledku v původním jazyce

This paper deals with automatic face recognition in the context of a real application for person identification developed for the Czech News Agency (ČTK). We focus on popular Local Binary Patterns (LPBs) that are frequently used in this field with high recognition accuracy. The main contribution consists in proposing and comparing several LBP-based approaches that detect important fiducial points fully automatically. We use a set of Gabor filters for this task. The proposed methods are evaluated on three standard corpora: ORL, FERET, AR face database and our ČTK dataset containing uncontrolled face images. Recognition results clearly show high quality of the proposed approaches that outperform significantly the baseline LBP approach on all corpora. The benefits of our methods are particularly evident in the case of real non controlled images (ČTK corpus) where the accuracy is increased by more than 20% in absolute value.

Název v anglickém jazyce

Local binary pattern based face recognition with automatically detected fiducial points

Popis výsledku anglicky

This paper deals with automatic face recognition in the context of a real application for person identification developed for the Czech News Agency (ČTK). We focus on popular Local Binary Patterns (LPBs) that are frequently used in this field with high recognition accuracy. The main contribution consists in proposing and comparing several LBP-based approaches that detect important fiducial points fully automatically. We use a set of Gabor filters for this task. The proposed methods are evaluated on three standard corpora: ORL, FERET, AR face database and our ČTK dataset containing uncontrolled face images. Recognition results clearly show high quality of the proposed approaches that outperform significantly the baseline LBP approach on all corpora. The benefits of our methods are particularly evident in the case of real non controlled images (ČTK corpus) where the accuracy is increased by more than 20% in absolute value.

Druh

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

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/LO1506" target="_blank" >LO1506: Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnost</a><br>

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

Integrated Computer-Aided Engineering

ISSN

1069-2509

e-ISSN

—

Svazek periodika

23

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

11

Strana od-do

129-139

Kód UT WoS článku

000372026000004

EID výsledku v databázi Scopus

2-s2.0-84960958491