DeepEthnic: Multi-Label Ethnic Classification from Face Images
This work addresses the problem of multi-label ethnic classification for applications in security or demographic analysis, but it is incremental as it builds on existing transfer learning methods.
The paper tackled ethnic group classification from face images using transfer learning from a pre-trained network, achieving state-of-the-art success rates of 99.02% for African, 99.76% for Asian, 99.2% for Caucasian, and 96.7% for Indian groups.
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.