Common Sparse Representation-based Robust Multimodal Biometrics Recognition

In this paper, we propose multitask multivairate common sparse representations for robust multimodal biometrics recognition which can be viewed as an extension of previous work on joint sparse representation-based multimodal biometrics recognition. The proposed algorithm can better utilize the discriminative information among different modalities simultaneously by enforcing the common sparse representation across all the modalities. Alternating direction method of multipliers is proposed to solve the resulting optimization problem. Extensive experiments on two biometrics datasets show that our method is robust and performs better than the state-of-the-art biometric fusion methods.