Although Support Vector Machine (SVM) is widely used in astronomy, it only takes the margin between classes into consideration while neglects the data distribution in each class, which seriously limits the classification efficiency. In view of this, a novel automatic classification method of star spectra data based on manifold-based discriminant analysis (MDA) and SVM is proposed in this paper. Two important concepts in MDA, manifold-based within-class scatter (MWCS) and manifold-based between-class scatter (MBCS), are introduced in the proposed method, the separating hyperplane found by which ensures MWCS is minimized and MBCS is maximized. Based on the above analysis, the corresponding optimal problem can be established, and then MDA transforms the original optimization problem to the QP dual form and we can obtain the support vectors and decision function. The classes of test samples are decided by the decision function. The advantage of the proposed method is that it not only focuses on the information between classes and distribution characteristics, but also preserves the manifold structure of each class. Experiments on SDSS star spectra datasets verify the effectiveness of the proposed method.