Lidar waveform features from the Ice, Cloud, and land Elevation Satellite/Geoscience Laser Altimeter System (ICESat/GLAS) and spectral features from Landsat Thematic Mapper (TM)/Enhanced TM Plus (ETM+) were used to discriminate land cover categories for GLAS footprints in Henan Province, China. Fifteen waveform metrics were derived from GLAS data while band ratios and surface spectral reflectance were taken from Landsat TM/ETM+. Random forest (RF) was used in feature selection and classification of footprints along with support vector machines (SVMs). The categories of classification included croplands, forests, shrublands, water bodies, and impervious surfaces. Compared with the use of waveform or spectral features alone in land cover classification, the joint use of waveform and spectral data as inputs improved the classification accuracy of footprints. An overall accuracy (OA) of 91% was achieved by either RF or SVM when features from both GLAS and Landsat sources were used increasing upon an accuracy of 85% if only one source was used. The high accuracy land cover data obtained by the joint use of the two data sources could be used as additional references in large scale land cover mapping when ground truth is hard to obtain. It is believed that the increase in accuracy is largely a result from the inclusion of the additional information of vertical structure offered by waveform lidar.