This paper presents a semi-supervised graph-based method for the classification of hyperspectral images. The method is designed to handle the special characteristics of hyperspectral images, namely high input dimension of pixels, low number of labeled samples, and spatial variability of the spectral signature. To alleviate these problems, the method incorporates three ingredients, respectively. First, being a kernel-based method, it combats the curse of dimensionality efficiently. Second, following a semi-supervised approach, it exploits the wealth of unlabeled samples in the image, and naturally gives relative importance to the labeled ones through a graph-based methodology. Finally, it incorporates contextual information through a full family of composite kernels. Noting that the graph method relies on inverting a huge kernel matrix formed by both labeled and unlabeled samples, we originally introduce the Nyström method in the formulation to speed up the classification process. The presented semi-supervised graph-based method is compared to state-of-the-art support vector machines (SVMs) in the classification of hyperspectral data. The proposed method produces better classification maps which capture the intrinsic structure collectively revealed by labeled and unlabeled points. Good and stable accuracy is produced in ill-posed classification problems (high dimensional spaces and low number of labeled samples). Also, the introduction of the composite kernels framework drastically improves results, and the new fast formulation ranks almost linearly in the computational Manuscript received September 2006; revised January 2007; G. Camps-Valls and T. V. Bandos are with Grup de Processament Digital de Senyals, GPDS. Dept. Enginyeria Electrònica. Escola Tècnica Superior d’Enginyeria. Universitat de València. C/ Dr. Moliner, 50. 46100 Burjassot (València) Spain. E-mail: firstname.lastname@example.org. D. Zhou is with Microsoft Research, One Microsoft Way Redmond, WA 98052. USA. E-mail: Dengyong.Zhou@microsoft.com February 13, 2007 DRAFT IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. XX, NO. Y, MONTH Z 2007 2 cost, rather than cubic as in the original method, thus allowing the use of this method in remote sensing applications.