Open-set Face Recognition using Ensembles trained on Clustered Data
This addresses scalable identification of unknown faces in security or surveillance, but it is incremental as it builds on existing methods.
The paper tackles open-set face recognition for galleries with hundreds to thousands of subjects by using clustering and an ensemble of binary learning algorithms to estimate if query faces belong to the gallery and retrieve identities, achieving competitive performance on LFW and YTF benchmarks.
Open-set face recognition describes a scenario where unknown subjects, unseen during the training stage, appear on test time. Not only it requires methods that accurately identify individuals of interest, but also demands approaches that effectively deal with unfamiliar faces. This work details a scalable open-set face identification approach to galleries composed of hundreds and thousands of subjects. It is composed of clustering and an ensemble of binary learning algorithms that estimates when query face samples belong to the face gallery and then retrieves their correct identity. The approach selects the most suitable gallery subjects and uses the ensemble to improve prediction performance. We carry out experiments on well-known LFW and YTF benchmarks. Results show that competitive performance can be achieved even when targeting scalability.