Poster
in
Affinity Workshop: Black in AI
FacEDiM: A Face Embedding Distribution Model for Few-Shot Biometric Authentication of Cattle
Meshia Cédric Oveneke · Rucha Vaishampayan · Deogratias Lukamba Nsadisa · Rucha Vaishampayan
Keywords: [ Deep Learning ] [ Applications of AI to Health ] [ Statistical Reasoning ] [ Computer Vision ]
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 1.18% for a FAR of 1.25% on a dataset of 20 cattle identities.