Deakin University
Browse

File(s) under permanent embargo

Atypical facial landmark localisation with stacked hourglass networks: a study on 3D facial modelling for medical diagnosis

chapter
posted on 2020-01-01, 00:00 authored by Gary Storey, Ahmed Bouridane, Richard Jiang, Chang-Tsun LiChang-Tsun Li
While facial biometrics has been widely used for identification purpose, it has recently been researched as medical biometrics for a range of diseases. In this chapter, we investigate the facial landmark detection for atypical 3D facial modelling in facial palsy cases, while potentially such modelling can assist the medical diagnosis using atypical facial features. In our work, a study of landmarks localisation methods such as stacked hourglass networks is conducted and evaluated to ascertain their accuracy when presented with unseen atypical faces. The evaluation highlights that the state-of-the-art stacked hourglass architecture outperforms other traditional methods.

History

Chapter number

3

Pagination

37-49

ISSN

2522-848X

eISSN

2522-8498

ISBN-13

9783030325824

Language

eng

Publication classification

B1 Book chapter

Extent

13

Editor/Contributor(s)

Jiang R, Li CT, Crookes D, Meng W, Rosenberger C

Publisher

Springer

Place of publication

Cham, Switzerland

Title of book

Deep biometrics

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC