# A Facial Feature Discovery Framework for Race Classification Using Deep Learning

arXiv: https://arxiv.org/abs/2104.02471 · HTML: https://mlsanity.com/paper/2104.02471/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 51 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 8 of 8)

- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [CNN: Single-label to Multi-label](https://mlsanity.com/paper/1406.5726/) (2014)
- [PANDA: Pose Aligned Networks for Deep Attribute Modeling](https://mlsanity.com/paper/1311.5591/) (2013)
- [Real-Time Facial Segmentation and Performance Capture from RGB Input](https://mlsanity.com/paper/1604.02647/) (2016)
- [A CNN Cascade for Landmark Guided Semantic Part Segmentation](https://mlsanity.com/paper/1609.09642/) (2016)
- [Learned Features are better for Ethnicity Classification](https://mlsanity.com/paper/1709.07429/) (2017)
- [Considering Race a Problem of Transfer Learning](https://mlsanity.com/paper/1812.04751/) (2018)

## Abstract (arXiv)

Race classification is a long-standing challenge in the field of face image analysis. The investigation of salient facial features is an important task to avoid processing all face parts. Face segmentation strongly benefits several face analysis tasks, including ethnicity and race classification. We propose a raceclassification algorithm using a prior face segmentation framework. A deep convolutional neural network (DCNN) was used to construct a face segmentation model. For training the DCNN, we label face images according to seven different classes, that is, nose, skin, hair, eyes, brows, back, and mouth. The DCNN model developed in the first phase was used to create segmentation results. The probabilistic classification method is used, and probability maps (PMs) are created for each semantic class. We investigated five salient facial features from among seven that help in race classification. Features are extracted from the PMs of five classes, and a new model is trained based on the DCNN. We assessed the performance of the proposed race classification method on four standard face datasets, reporting superior results compared with previous studies.