FacEDiM: A Face Embedding Distribution Model for Few-Shot Biometric Authentication of Cattle

• DOI: 10.48550/arxiv.2302.14831
• Publication Date: 2023-01-01
• Authors: Meshia Cédric Ove...; Rucha Vaishampayan; Deogratias Lukamb...; Jenny Ambukiyenyi...
• Keywords: Mahalanobis distance

This work proposes to solve the problem of few-shot biometric authentication by computing Mahalanobis distance between testing embeddings and a multivariate Gaussian distribution training obtained using pre-trained CNNs. Experimental results show that models on ImageNet dataset significantly outperform human faces. With VGG16 model, we obtain FRR 1.25% for FAR 1.18% 20 cattle identities.