This project proposes methods for classifying scenes in remote sensing images. It compares the accuracy of traditional bag-of-visual-words (BoVW) models using handcrafted features to a bag-of-convolutional features (BoCF) model using deep learning. It also applies a grey wolf optimizer (GWO) algorithm for image segmentation. Results show BoCF doubled the accuracy of BoVW, and combining BoVW with GWO improved accuracy over BoVW alone. The project concludes more work is needed to better combine remote sensing data and deep learning for classification.