We propose a hybrid face recognition method that combines holistic and feature analysis-based approaches using a Markov random field (MRF) model. The face images are divided into small patches, and the MRF model is used to represent the relationship between the image patches and the patch ID's. The MRF model is first learned from the training image patches, given a test image. The most probable patch ID's is then inferred using the belief propagation (BP) algorithm. Finally, the ID of the test image is determined by a voting scheme from the estimated patch ID's. Experimental results on several face datasets indicate the significant potential of our method.