A Data-augmented 3D Morphable Model of the Ear

Hang Dai; Nicholas Edwin Pears; William Alfred Peter Smith

A Data-augmented 3D Morphable Model of the Ear

Hang Dai, Nicholas Edwin Pears, William Alfred Peter Smith

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Morphable models are useful shape priors for biometric recognition tasks.
Here we present an iterative process of refinement for a 3D Morphable Model (3DMM) of the human ear that employs data augmentation. The process employs the following stages
1) landmark-based 3DMM fitting; 2) 3D template deformation to overcome noisy over-fitting; 3) 3D mesh editing, to improve the fit to manual 2D landmarks. These processes are wrapped in an iterative procedure that is able to bootstrap a weak, approximate model into a significantly better model. Evaluations using several performance metrics verify the improvement of our model using the proposed algorithm. We use this new 3DMM model-booting algorithm to generate a refined 3D morphable model of the human ear, and we make this new model and our augmented training dataset public.

Original language	English
Title of host publication	The 13th IEEE International Conference on AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2018)
Publisher	IEEE
Number of pages	5
ISBN (Print)	9781538623350
Publication status	Published - 15 May 2018

Bibliographical note

© 2018 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

Keywords

3D Morphable Model; 3D shape registration; 3D image analysis

Access to Document

A Data-augmented 3D Morphable Model of the Ear
© 2018 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details
Final published version, 3.72 MB

Nick Pears
- nick.pearsyork.acuk
- Computer Science - Professor
Person: Academic

Cite this

@inproceedings{0229c0875e2e492aa6e549fa2a35f043,

title = "A Data-augmented 3D Morphable Model of the Ear",

abstract = "Morphable models are useful shape priors for biometric recognition tasks.Here we present an iterative process of refinement for a 3D Morphable Model (3DMM) of the human ear that employs data augmentation. The process employs the following stages1) landmark-based 3DMM fitting; 2) 3D template deformation to overcome noisy over-fitting; 3) 3D mesh editing, to improve the fit to manual 2D landmarks. These processes are wrapped in an iterative procedure that is able to bootstrap a weak, approximate model into a significantly better model. Evaluations using several performance metrics verify the improvement of our model using the proposed algorithm. We use this new 3DMM model-booting algorithm to generate a refined 3D morphable model of the human ear, and we make this new model and our augmented training dataset public.",

keywords = "3D Morphable Model; 3D shape registration; 3D image analysis",

author = "Hang Dai and Pears, {Nicholas Edwin} and Smith, {William Alfred Peter}",

note = "{\textcopyright} 2018 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details",

year = "2018",

month = may,

day = "15",

language = "English",

isbn = "9781538623350",

booktitle = "The 13th IEEE International Conference on AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2018)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - A Data-augmented 3D Morphable Model of the Ear

AU - Dai, Hang

AU - Pears, Nicholas Edwin

AU - Smith, William Alfred Peter

N1 - © 2018 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

PY - 2018/5/15

Y1 - 2018/5/15

N2 - Morphable models are useful shape priors for biometric recognition tasks.Here we present an iterative process of refinement for a 3D Morphable Model (3DMM) of the human ear that employs data augmentation. The process employs the following stages1) landmark-based 3DMM fitting; 2) 3D template deformation to overcome noisy over-fitting; 3) 3D mesh editing, to improve the fit to manual 2D landmarks. These processes are wrapped in an iterative procedure that is able to bootstrap a weak, approximate model into a significantly better model. Evaluations using several performance metrics verify the improvement of our model using the proposed algorithm. We use this new 3DMM model-booting algorithm to generate a refined 3D morphable model of the human ear, and we make this new model and our augmented training dataset public.

AB - Morphable models are useful shape priors for biometric recognition tasks.Here we present an iterative process of refinement for a 3D Morphable Model (3DMM) of the human ear that employs data augmentation. The process employs the following stages1) landmark-based 3DMM fitting; 2) 3D template deformation to overcome noisy over-fitting; 3) 3D mesh editing, to improve the fit to manual 2D landmarks. These processes are wrapped in an iterative procedure that is able to bootstrap a weak, approximate model into a significantly better model. Evaluations using several performance metrics verify the improvement of our model using the proposed algorithm. We use this new 3DMM model-booting algorithm to generate a refined 3D morphable model of the human ear, and we make this new model and our augmented training dataset public.

KW - 3D Morphable Model; 3D shape registration; 3D image analysis

M3 - Conference contribution

SN - 9781538623350

BT - The 13th IEEE International Conference on AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2018)

PB - IEEE

ER -

A Data-augmented 3D Morphable Model of the Ear

Abstract

Bibliographical note

Keywords

Access to Document

Profiles

Nick Pears

Cite this