In our work, we look to classify images that make their way into our smartphone devices through various social-media text-messaging platforms. We aim at classifying images into three broad categories: document-based images, quote-based images, and photographs. People, especially students, share many document-based images that include snapshots of essential emails, handwritten notes, articles, etc. Quote based images, consisting of birthday wishes, motivational messages, festival greetings, etc., are among the highly shared images on social media platforms. A significant share of images constitutes photographs of people, including group photographs, selfies, portraits, etc. We train various convolutional neural network (CNN) based models on our self-made dataset and compare their results to find our task’s optimum model.