300 Faces In-The-Wild Challenge: database and results

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/facial-point-annotations/.

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

“…Although deformable models can be built for a variety of object classes, the majority of ongoing research has focused on the task of facial alignment. Recent largescale challenges on facial alignment (Sagonas et al 2013b(Sagonas et al , a, 2015 are characteristic examples of the rapid progress being made in the field. Currently, the most commonly-used and well-studied face alignment methods can be separated into two major families: (i) discriminative models that employ regression in a cascaded manner, and (ii) generative models that are iteratively optimised.…”

“…Each video includes only one person and is annotated using the 68 point mark-up employed by Gross et al (2010) and Sagonas et al (2015) for Multi-PIE and 300W databases, respectively. All videos include between 1500 frames and 3000 frames with a large variety of expressions, poses and capturing conditions, which makes the dataset very challenging for deformable facial tracking.…”

“…All the landmark localisation methods were trained with respect to the 68 facial points mark-up employed by Sagonas et al (2013aSagonas et al ( , 2015 in 300W, while the rest of the parameters were determined via cross-validation. Again, this validation set consisted of frames from the 300 VW trainset, as well as 60 privately collected images with challenging poses.…”

“…Much of this progress can be attributed to the release of large annotated datasets of facial landmarks (Sagonas et al 2013b, a;Zhu and Ramanan 2012;Le et al 2012;Belhumeur et al 2013;Köstinger et al 2011) and very recently the area of facial landmark localisation has become extremely competitive with recent works including Xiong and De la Torre (2013), Ren et al (2014), Kazemi and Sullivan (2014), Zhu et al (2015), Tzimiropoulos (2015). For a recent evaluation of facial landmark localisation methods the interested reader may refer to the survey by Wang et al (2014) and to the results of the 300 W competition by Sagonas et al (2015). Finally, face recognition and verification are extremely popular lines of research.…”

Recovering Joint and Individual Components in Facial Data

“…In order to effectively recover the joint and common components, the faces of each dataset should be put in correspondence. Therefore, their N = 68 facial landmark points are localized using the detector [32], [33] and subsequently employed to compute a mean reference shape. Then, the faces of each dataset are warped into a corresponding reference shape by using the piecewise affine warp function W(·) [34].…”