Sift And Gabor Features For Very High Resolution Image Classification

this paper presents a new approach to extract features from high resolution images inspired by the sift descriptor and gabor features. both of these two methods are powerful when used separately or together in region-based or pixel-based classification, they brought a high accuracy. our approach was applied to classify two very high resolution images of boumerdes (algeria) and djeddah $(ksa)$ using knn and svm. the obtained results achieved promising performance compared to using spectral information alone.