In this paper, a combination method, between the neural network and textures information, is proposed to remote sensing images classification. The methodology involves an extraction of texture features using the gray level co-occurrence matrix and image classification with BP artificial neural network. The combination of texture features and the digital elevation model (DEM) as classified bands to neural network were used to recognized different classes. This scheme shows high recognition accuracy in the classification of remote sensing images. In the experiments, the proposed method was successfully applied to remote sensing image classification and Land Use Change Detection, in the meanwhile, the effectiveness of the proposed method was verified.