Local binary pattern based face recognition with automatically detected fiducial points

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

Local binary pattern based face recognition with automatically detected fiducial points

Original language description

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.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

IN - Informatics

OECD FORD branch

—

Project

<a href="/en/project/LO1506" target="_blank" >LO1506: Sustainability support of the centre NTIS - New Technologies for the Information Society</a><br>

Continuities

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

Publication year

2016

Confidentiality

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

Name of the periodical

Integrated Computer-Aided Engineering

ISSN

1069-2509

e-ISSN

—

Volume of the periodical

23

Issue of the periodical within the volume

2

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

11

Pages from-to

129-139

UT code for WoS article

000372026000004

EID of the result in the Scopus database

2-s2.0-84960958491