DeepEthnic: Multi-Label Ethnic Classification from Face Images

TL;DR

This paper introduces DeepEthnic, a transfer learning-based method for multi-label ethnic classification from face images, achieving state-of-the-art accuracy across four major ethnic groups.

Contribution

It presents a novel application of transfer learning for ethnic classification, significantly improving accuracy over traditional methods.

Findings

Achieved over 99% accuracy for African, Asian, and Caucasian groups.

Achieved 96.7% accuracy for Indian ethnicity.

Demonstrated the effectiveness of transfer learning in ethnic classification.

Abstract

Ethnic group classification is a well-researched problem, which has been pursued mainly during the past two decades via traditional approaches of image processing and machine learning. In this paper, we propose a method of classifying an image face into an ethnic group by applying transfer learning from a previously trained classification network for large-scale data recognition. Our proposed method yields state-of-the-art success rates of 99.02%, 99.76%, 99.2%, and 96.7%, respectively, for the four ethnic groups: African, Asian, Caucasian, and Indian.