The classification accuracy is unsatisfactory in the complicated terrain area of the Loess Plateau when the single supervised classification is used in remote sensing. The paper discusses the extraction of classification information of Yan. an City and nearby area from a TM image and deals w ith the image classification based on the SVM method integrating the information of M NF,NDVI,and DEM.In comparison with Max-imum Likelihood and SVM method of single spectrum, results showed that the objects with the same spectrum are distinguished by using DEM in image classification. Compared with the traditional classification method, the classification based on the information of DEM and multiple bands supported with the SVM method can acquire hig her classification effect.