The supervised learning method described in this project extracts low level features such as edges, textures, RGB values, HSV values, location , number of line pixels per superpixel etc. to train the model using a Support Vector Machine and semantically label the superpixels in test set with labels such as sky, tree, road, grass, water, building, mountains & foreground objects. The results were then compared with ground truth to evaluate the accuracy of the model.
Tools used : Matlab, LibSVM, VLFeat