This work proposes to solve the problem of few-shot biometric authentication by computing the Mahalanobis distance between testing embeddings and a multivariate Gaussian distribution of training embeddings obtained using pre-trained CNNs. Experimental results show that models pre-trained on the ImageNet dataset significantly outperform models pre-trained on human faces. With a VGG16 model, we obtain a FRR of 1.25% for a FAR of 1.18% on a dataset of 20 cattle identities.
@article{arxiv.2302.14831,
title = {FacEDiM: A Face Embedding Distribution Model for Few-Shot Biometric Authentication of Cattle},
author = {Meshia Cédric Oveneke and Rucha Vaishampayan and Deogratias Lukamba Nsadisa and Jenny Ambukiyenyi Onya},
journal= {arXiv preprint arXiv:2302.14831},
year = {2023}
}
Comments
4 pages, 1 figure, 1 table, paper accepted at Black In AI at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, USA