A novel face recognition method based on multi-features using a neural networks committee (NNC) machine is proposed in this paper. The committee consists of several independent neural networks trained by different image blocks of the original images in different feature domains. The final classification results represent a combined response of the individual networks. Then, we use the designed neural networks committee to perform human face data recognition. The experimental results show that the classification accuracy of our proposed NNC is much higher than that of single feature domain.