Atypical Facial Landmark Localisation with Stacked Hourglass Networks: A Study on 3D Facial Modelling for Medical Diagnosis

09/05/2019
by   Gary Storey, et al.
0

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.

READ FULL TEXT

page 2

page 13

page 14

research
08/23/2016

Failure Detection for Facial Landmark Detectors

Most face applications depend heavily on the accuracy of the face and fa...
research
07/30/2020

The Blessing and the Curse of the Noise behind Facial Landmark Annotations

The evolving algorithms for 2D facial landmark detection empower people ...
research
05/17/2019

Limitations and Biases in Facial Landmark Detection -- An Empirical Study on Older Adults with Dementia

Accurate facial expression analysis is an essential step in various clin...
research
11/24/2019

Facial Landmark Correlation Analysis

We present a facial landmark position correlation analysis as well as it...
research
04/16/2021

Accurate 3D Facial Geometry Prediction by Multi-Task, Multi-Modal, and Multi-Representation Landmark Refinement Network

This work focuses on complete 3D facial geometry prediction, including 3...
research
03/20/2021

Automatic Quantification of Facial Asymmetry using Facial Landmarks

One-sided facial paralysis causes uneven movements of facial muscles on ...

Please sign up or login with your details

Forgot password? Click here to reset