Coupled Kernel Embedding for Low-Resolution Face Image Recognition

Practical video scene and face recognition systems are sometimes confronted with low-resolution (LR) images. The faces may be very small even if the video is clear, thus it is difficult to directly measure the similarity between the faces and the high-resolution (HR) training samples. Face recognition based on traditional super-resolution (SR) methods usually have limited performance because the target of SR may not be consistent with that of classification, and time-consuming SR algorithms are not suitable for real-time applications. In this paper, a new feature extraction method called coupled kernel embedding (CKE) is proposed for LR face recognition without any SR preprocessing. In this method, the final kernel matrix is constructed by concatenating two individual kernel matrices in the diagonal direction, and the (semi)positively definite properties are preserved for optimization. CKE addresses the problem of comparing multimodal data that are difficult for conventional methods in practice due to the lack of an efficient similarity measure. Particularly, different kernel types (e.g., linear, Gaussian, polynomial) can be integrated into a uniform optimization objective, which cannot be achieved by simple linear methods. CKE solves this problem by minimizing the dissimilarities captured by their kernel Gram matrices in the LR and HR spaces. In the implementation, the nonlinear objective function is minimized by a generalized eigenvalue decomposition. Experiments on benchmark and real databases show that our CKE method indeed improves the recognition performance.