Deep Learning in Visual Computing

CHAPTER 6 The Nose and Ethnicity

The nose is the most central feature on the face, which is known to exhibit both gender and ethnic differences. It is a robust feature, invariant to expression, and known to contain depth information. In this chapter, we show how deep learning can be utilised for binary ethnicity classification from images of the nose. We show this through a series of experiments using pre-trained deep learning models such as the ResNet-50, ResNet-101, ResNet-152, VGG-Face, VGG-16, and VGG-19, for feature extraction and a linear Support Vector Machine for classification.

Introduction

It is well established that facial morphology shows a great deal of variation across racial and ethnic groups. This is especially true in the case ...