Endoscopy is the gold standard for examination and diagnosis in the gastrointestinal (GI) tract. A large volume of images is typically captured during endoscopy. Reviewing such images requires significant time and experience. We propose a superpixel-based technique for segmenting and classifying GI landmarks and diseases. We split each image into superpixels from which we extract several texture and color features. We trained multiple superpixel classifiers based on combinations of these features and obtained AUC values of 82.06%, 99.6%, and 97.4% in the classification of the upper, middle, and lower GI parts, respectively. Our superpixel-based classifiers outperformed pixel-based ones.