Dense Surface Point Distribution Models of the Human Face

Authors:
Tim J. Hutton;Bernard F. Buxton;Peter Hammond
Affiliations:
-;-;-
Venue:
MMBIA '01 Proceedings of the IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA'01)
Year:
2001

Citing 0
Cited 9

Building and Testing a Statistical Shape Model of the Human Ear Canal

MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part II
Implicit, view invariant, linear flexible shape modelling

Pattern Recognition Letters - Special issue: Advances in pattern recognition
Bayes Reconstruction of Missing Teeth

Journal of Mathematical Imaging and Vision
Multimorphing: A tool for shape synthesis and analysis

Advances in Engineering Software
Some issues of biological shape modelling with applications

SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Reconstructing teeth with bite information

SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Assessing the uniqueness and permanence of facial actions for use in biometric applications

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special issue on recent advances in biometrics
Statistical face models for the prediction of soft-tissue deformations after orthognathic osteotomies

MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II
Transferring a labeled generic rig to animate face models

AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we show how a dense surface model of the human face can be built from a population of examples. A technique that combines active shape models (ASMs) withiterative closest point (ICP) can be used to fit the model to new faces. The model is built by aligning the surfaces using a sparse set of hand-placed landmarks, then using thin-plate spline warping to make a dense correspondence with a base mesh. All of the mesh vertices are then used as land-marks to build a 3D point distribution model. The dense surface point distribution model is more sensitive than the landmark model to correlated facial characteristics such asgender, age and the presence of congenital abnormalities.