300 faces In-the-wild challenge: database and results
File(s)300w.pdf (4.19 MB)
Accepted version
Author(s)
Sagonas, C
Antonakos, E
Tzimiropoulos, G
Zafeiriou, S
Pantic, M
Type
Journal Article
Abstract
Computer Vision has recently witnessed great research advance towards automatic facial points detection. Numerous methodologies have been proposed during the last few years that achieve accurate and efficient performance. However, fair comparison between these methodologies is infeasible mainly due to two issues. (a) Most existing databases, captured under both constrained and unconstrained (in-the-wild) conditions have been annotated using different mark-ups and, in most cases, the accuracy of the annotations is low. (b) Most published works report experimental results using different training/testing sets, different error metrics and, of course, landmark points with semantically different locations. In this paper, we aim to overcome the aforementioned problems by (a)proposing a semi-automatic annotation technique that was employed to re-annotate most existing facial databases under a unified protocol, and (b)presenting the 300 Faces In-The-Wild Challenge (300-W), the first facial landmark localization challenge that was organized twice, in 2013 and 2015. To the best of our knowledge, this is the first effort towards a unified annotation scheme of massive databases and a fair experimental comparison of existing facial landmark localization systems. The images and annotations of the new testing database that was used in the 300-W challenge are available from http://ibug.doc.ic.ac.uk/resources/300-W_IMAVIS/.
Date Issued
2016-01-25
Date Acceptance
2016-01-04
Citation
Image and Vision Computing, 2016, 47, pp.3-18
ISSN
0262-8856
Publisher
Elsevier
Start Page
3
End Page
18
Journal / Book Title
Image and Vision Computing
Volume
47
Copyright Statement
© 2016 Elsevier B.V. All rights reserved. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
Sponsor
Engineering & Physical Science Research Council (EPSRC)
Engineering & Physical Science Research Council (EPSRC)
Grant Number
EP/J017787/1
EP/L026813/1
Subjects
Science & Technology
Technology
Physical Sciences
Computer Science, Artificial Intelligence
Computer Science, Software Engineering
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
Optics
Computer Science
Engineering
Facial landmark localization
Challenge
Semi-automatic annotation tool
Facial database
ACTIVE APPEARANCE MODELS
PICTORIAL STRUCTURES
POSE ESTIMATION
ALIGNMENT
RECOGNITION
FEATURES
Artificial Intelligence & Image Processing
0801 Artificial Intelligence And Image Processing
0906 Electrical And Electronic Engineering
Publication Status
Published