In this paper, we present a face detection approach by combining multiple experts. We use four detection experts differing in feature representation of local images: intensity, gradient, Gabor, and 2D Haar wavelet. The four experts employ the same classification model, namely, a polynomial neural network (PNN) on reduced feature subspace learned by principal component analysis (PCA). The outputs of the four PNNs are fused to make the final decision of face detection. In experiments on a large number of images, the multi-expert approach has yielded significant improvements compared to the best individual expert and the state-of-the-art methods proposed in the literature.