InFER: A Multi-Ethnic Indian Facial Expression Recognition Dataset

TL;DR

This paper introduces InFER, a comprehensive multi-ethnic Indian facial expression dataset with over 10,000 images and videos, designed to improve deep learning FER systems by capturing diverse ethnic and expressive variations.

Contribution

The creation of the first large-scale, multi-ethnic Indian FER dataset with both posed and spontaneous expressions, enabling more inclusive and accurate FER system development.

Findings

Baseline deep FER methods achieve promising results on InFER.

The dataset highlights the importance of ethnic diversity in FER training.

InFER facilitates real-world FER applications in multi-ethnic contexts.

Abstract

The rapid advancement in deep learning over the past decade has transformed Facial Expression Recognition (FER) systems, as newer methods have been proposed that outperform the existing traditional handcrafted techniques. However, such a supervised learning approach requires a sufficiently large training dataset covering all the possible scenarios. And since most people exhibit facial expressions based upon their age group, gender, and ethnicity, a diverse facial expression dataset is needed. This becomes even more crucial while developing a FER system for the Indian subcontinent, which comprises of a diverse multi-ethnic population. In this work, we present InFER, a real-world multi-ethnic Indian Facial Expression Recognition dataset consisting of 10,200 images and 4,200 short videos of seven basic facial expressions. The dataset has posed expressions of 600 human subjects, and spontaneous/acted expressions of 6000 images crowd-sourced from the internet. To the best of our knowledge InFER is the first of its kind consisting of images from 600 subjects from very diverse ethnicity of the Indian Subcontinent. We also present the experimental results of baseline & deep FER methods on our dataset to substantiate its usability in real-world practical applications.