300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge

Abstract

Automatic facial point detection plays arguably the most important role in face analysis. Several methods have been proposed which reported their results on databases of both constrained and unconstrained conditions. Most of these databases provide annotations with different mark-ups and in some cases the are problems related to the accuracy of the fiducial points. The aforementioned issues as well as the lack of a evaluation protocol makes it difficult to compare performance between different systems. In this paper, we present the 300 Faces in-the-Wild Challenge: The first facial landmark localization Challenge which is held in conjunction with the International Conference on Computer Vision 2013, Sydney, Australia. The main goal of this challenge is to compare the performance of different methods on a new-collected dataset using the same evaluation protocol and the same mark-up and hence to develop the first standardized benchmark for facial landmark localization.

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

“…Following this, Gauss-Newton optimisation has been the modern method for optimising AAMs. Numerous extensions have been published, either related to the optimisation procedure (Papandreou and In recent challenges by Sagonas et al (2013aSagonas et al ( , 2015, discriminative methods have been shown to represent the current state-of-the-art. However, in order to enable a fair comparison between types of methods we selected a representative set of landmark localisation methods to compare with in this paper.…”

“…We chose to use ERT (Kazemi and Sullivan 2014) as it is extremely fast and the implementation provided by King (2009) is the best known implementation of a tree-based regressor. We chose CFSS (Zhu et al 2015) as it is the current state-of-the-art on the data provided by the 300W competition of Sagonas et al (2013a). We used the Gauss-Newton Part-based AAM of …”

“…-The establishment of in-the-wild benchmarks and challenges that provide a fair comparison between state of the art techniques. FDDB (Jain and Learned-Miller 2010), 300 W (Sagonas et al 2013a(Sagonas et al , 2015 and Janus (Klare et al 2015) are the most characteristic examples for face detection, facial landmark localisation and face recognition, respectively.…”

A survey on face detection in the wild: Past, present and future

“…These landmarks were used to drive the annotation process of the AFLW database with regards to facial bounding boxes [26]. Finally, other databases that can be used for training face detection algorithms are the LFPW [199], HELEN [200] and iBUG databases [197], since facial landmark annotations are provided by the database creators.…”

“…Furthermore, the faces have been annotated with regards to 6 facial landmarks (the center of eyes, tip of nose, the two corners and center of mouth) and labelled discretized viewpoints (−90 o to 90 o every 15 o ) along pitch and yaw directions and (left, center, right) viewpoints along the roll direction. This database was recently expanded to 68 landmarks [197]. Another database that was used for training 'in-the-wild' face detection algorithms is the AFLW database [198] which has been annotated with 21 landmarks.…”