Against the backdrop of growing concerns about security, face-based biometrics has emerged as a methodology to reliably infer human identity. Active learning algorithms automatically select appropriate data samples to train a classifier and reduce human effort in annotating data instances. In this work, a novel optimization based batch mode active learning strategy has been applied to face recognition. The flexibility of the framework is corroborated by its ability to incorporate additional available information. Our results on the VidTIMIT and the NIST MBGC datasets certify the potential of this method in being used for real world biometric applications. © 2012 Elsevier Ltd.