We propose a novel face recognition method that represents and classifies face images in the feature space. It first assumes that in the feature space the test sample can be well expressed by a linear combination of the training samples, and then it exploits the obtained linear combination to perform face recognition. We also present the foundation, rationale, and characteristics of, as well as the differences between, our method and conventional kernel methods. The analysis shows that our method is a representation-based kernel method and works in the feature space. This method might be able to outperform the representation-based methods that work in the original space. The experimental results show that our method partially possesses the properties of "sparseness" and is able to reduce greatly the effects of noise and occlusion in the test sample.