Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

3D geometry-based automatic landmark localization in presence of facial occlusions

3D geometry-based automatic landmark localization in presence of facial occlusions This study proposes a novel automatic method for facial landmark localization relying on geometrical properties of 3D facial surface working both on complete faces displaying different emotions and in presence of occlusions. In particular, 12 descriptors coming from Differential Geometry including the coefficients of the fundamental forms, Gaussian, mean, principal curvatures, shape index and curvedness are extracted as facial features and their local geometric properties are exploited to localize 13 soft-tissue landmarks from eye and nose areas. The method is deterministic and is backboned by a thresholding technique designed by studying the behaviour of each geometrical descriptor in correspondence to the locus of each landmark. Occlusions are managed by a detection algorithm based on geometrical properties which allows to proceed with the landmark localization avoiding the covered areas. Experimentations were carried out on 3132 faces of the Bosphorus database and of a 230-sized internal database, including expressive and occluded ones (mouth, eye, and eyeglasses occlusions), obtaining 4.75 mm mean localization error. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Multimedia Tools and Applications Springer Journals

3D geometry-based automatic landmark localization in presence of facial occlusions

Download PDF
29 pages

Loading next page...
 
/lp/springer_journal/3d-geometry-based-automatic-landmark-localization-in-presence-of-doPI0tIkBK
Publisher
Springer Journals
Copyright
Copyright © 2017 by Springer Science+Business Media, LLC
Subject
Computer Science; Multimedia Information Systems; Computer Communication Networks; Data Structures, Cryptology and Information Theory; Special Purpose and Application-Based Systems
ISSN
1380-7501
eISSN
1573-7721
DOI
10.1007/s11042-017-5025-y
Publisher site
See Article on Publisher Site

Abstract

This study proposes a novel automatic method for facial landmark localization relying on geometrical properties of 3D facial surface working both on complete faces displaying different emotions and in presence of occlusions. In particular, 12 descriptors coming from Differential Geometry including the coefficients of the fundamental forms, Gaussian, mean, principal curvatures, shape index and curvedness are extracted as facial features and their local geometric properties are exploited to localize 13 soft-tissue landmarks from eye and nose areas. The method is deterministic and is backboned by a thresholding technique designed by studying the behaviour of each geometrical descriptor in correspondence to the locus of each landmark. Occlusions are managed by a detection algorithm based on geometrical properties which allows to proceed with the landmark localization avoiding the covered areas. Experimentations were carried out on 3132 faces of the Bosphorus database and of a 230-sized internal database, including expressive and occluded ones (mouth, eye, and eyeglasses occlusions), obtaining 4.75 mm mean localization error.

Journal

Multimedia Tools and Applications – Springer Journals

Published: Jul 27, 2017

References

  • 2D and 3D face recognition: a survey
    Abate, AF; Nappi, M; Riccio, D; Sabatino, G
  • A machine-learning approach to keypoint detection and landmarking on 3D meshes
    Creusot, C; Pears, N; Austin, J
  • An efficient multimodal 2D+ 3D feature-based approach to automatic facial expression recognition
    Ding, H; Huang, H; Wang, D; Zhao, Y; Li, X; Morvan, JM; Chen, L
  • COSMOS-A representation scheme for 3D free-form objects
    Dorai, C; Jain, AK
  • Surface shape and curvature scales
    Koenderink, JJ; Doorn, AJ
  • Automatic ear landmark localization, segmentation, and pose classification in range images
    Lei, J; You, X; Abdel-Mottaleb, M
  • Farkas, Anthropometry of the Head and Face in Medicine
    Leslie, G
  • Farkas, Anthropometry of the head and face (ed 2)
    Leslie, G
  • Nose tip detection on three-dimensional faces using pose-invariant differential surface features
    Li, Y; Wang, Y; Wang, B; Sui, L
  • 3D facial landmark detection under large yaw and expression variations
    Perakis, P; Passalis, G; Theoharis, T; Kakadiaris, IA
  • Feature fusion for facial landmark detection
    Perakis, P; Theoharis, T; Kakadiaris, IA
  • 3-d facial landmark localization with asymmetry patterns and shape regression from incomplete local features
    Sukno, FM; Waddington, JL; Whelan, PF
  • Geometrical descriptors for human face morphological analysis and recognition
    Vezzetti, E; Marcolin, F
  • 3D Landmarking in multiexpression face analysis: a preliminary study on eyebrows and mouth
    Vezzetti, E; Marcolin, F
  • Novel descriptors for geometrical 3D face analysis
    Vezzetti, E; Marcolin, F
  • A pose-independent method for 3D face landmark formalization
    Vezzetti, E; Moos, S; Marcolin, F; Stola, V
  • Exploiting 3D ultrasound for fetal diagnosis purpose through facial landmarking
    Vezzetti, E; Speranza, D; Marcolin, F; Fracastoro, G
  • 3D face recognition: an automatic strategy based on geometrical descriptors and landmarks
    Vezzetti, E; Marcolin, F; Fracastoro, G