Point-Triplet Descriptors for 3D Facial Landmark Localisation

An investigation to localise facial landmarks from 3D images is presented, without using any assumption concerning facial pose. This paper introduces new surface descriptors, which are derived from either unstructured face data, or a radial basis function (RBF) model of the facial surface. Two new variants of feature descriptors are described, generally named as point -- triplet descriptors because they require three vertices to be computed. The first is related to the classical depth map feature, which is referred to as weighted -- interpolated depth map. The second variant of descriptors are derived from an implicit RBF model, they are referred to as surface RBF signature (SRS) features. Both variants of descriptors are able to encode surface information within a triangular region defined by a point -- triplet into a surface signature, which could be useful not only for 3D face processing but also within a number of graph based retrieval applications. These descriptors are embedded into a system designed to localise the nose -- tip and two inner -- eye corners. Landmark localisation performance is reported by computing errors of estimated landmark locations against our respective ground -- truth data from the Face Recognition Grand Challenge (FRGC) database.

[1]  M. Romero-Huertas,et al.  3D Facial Landmark Localisation by Matching Simple Descriptors , 2008, 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems.

[2]  M MartínezAleix Recognizing Imprecisely Localized, Partially Occluded, and Expression Variant Faces from a Single Sample per Class , 2002 .

[3]  Maja Pantic,et al.  Automatic Analysis of Facial Expressions: The State of the Art , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Nick Pears,et al.  From 3D Point Clouds to Pose-Normalised Depth Maps , 2010, International Journal of Computer Vision.

[5]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[6]  Aleix M. Martínez,et al.  Recognizing Imprecisely Localized, Partially Occluded, and Expression Variant Faces from a Single Sample per Class , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Nick Pears,et al.  Point-pair descriptors for 3D facial landmark localisation , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[9]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[10]  Jim Austin,et al.  3D face landmark labelling , 2010, 3DOR '10.

[11]  Berk Gökberk,et al.  Regional Registration for Expression Resistant 3-D Face Recognition , 2010, IEEE Transactions on Information Forensics and Security.

[12]  Nick Pears,et al.  Landmark Localisation in 3D Face Data , 2009, 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance.

[13]  Rama Chellappa,et al.  Face Processing: Advanced Modeling and Methods , 2006, J. Electronic Imaging.

[14]  Youssef Meguebli,et al.  The spiral facets: A unified framework for the analysis and description of 3D facial mesh surface , 2010, VISAPP.