Low-resolution face recognition with single sample per person

As a growing number of low-resolution (LR) face images are captured by surveillance cameras, LR face recognition has been a hot issue for recent years. Previous efforts on LR face recognition typically assume each subject has multiple high-resolution (HR) training samples. However, this assumption may not hold in some special cases such as law-enforcement where only a single HR sample per person exists in the training set. For LR face recognition in SSPP scenario, it often suffers from overfitting and singular matrix problems. In this paper, we are the first to investigate LR face recognition with single sample per person, and propose a cluster-based regularized simultaneous discriminant analysis (C-RSDA) method based on SDA. C-RSDA regularizes the between-class and within-class scatter matrices respectively with intercluster and intra-cluster scatter matrices, where the cluster-based scatter matrices are computed from unsupervised clustering. With the cluster-based scatter matrices, not only the singularity problem is resolved, but overfitting problem is overcomed as more variations are exploited from the limited training samples. Thus, the proposed C-RSDA enhances the discriminative power of the feature subspace. We extensively evaluate C-RSDA on recognizing LR face images captured in both controlled and uncontrolled environments. The encouraging experimental results demonstrate the effectiveness of the proposed ap-