Abstract: In hyperspectral image classification labeled samples is difficult to obtain. Semisupervised classification method can make use of the information contained in the large number of unlabeled samples to improve the classification accuracy. Transductive support vector machine (TSVM) is an extension of the support vector machine (SVM) in the semisupervised learning. In this paper we use Concave-Convex Procedure (CCCP) to optimize the nonconvex objective function of TSVM. The noconvex function is decomposed into the combination of convex part and concave part. So the problem is changed into an convex optimization problem. In hyperspectral image, each band’s ability to distinguish different material is not in the same range. In order to make a better use of bands' classification abilities, the spectrally weighted vector is introduced. Then the kernel function is modified by the spectrally weighted vector. So different bands have different weighted values. Experiments show that the proposed method has shown superiority in the classification accuracy and the use of sample size. Thus the proposed method can be applicable to large-scale hyperspectral image classification.