The classification of hyperspectral images (HSIs) is a hot topic in the field of remote sensing technology. In recent years, convolutional neural network (CNN) has achieved great success for HSI classification. However, CNN has to do a great effort in parameters tuning which is time-consuming. Furthermore, a large number of samples are required to train CNN, nevertheless, it is expensive to obtain enough training samples from HSIs. In this paper, we propose a novel classification approach based on deep forest. To reduce the dimension of hyperspectral data, principal component analysis (PCA) is performed during the pre-processing. In contrast to the CNN, our method has fewer hyper-parameters and faster training speed. To the best of our knowledge, this is among the first deep forest-based hyperspectral spectral information classification. Extensive experiments are conducted on two real-world HSI datasets to show the proposed method is significantly superior to the state-of-the-art methods.