Anthropomorphic robots, or robots with human-like appearance features such as eyes, hands, or faces, have drawn considerable attention in recent years. To date, what makes a robot appear human-like has been driven by designers' and researchers' intuitions, because a systematic understanding of the range, variety, and relationships among constituent features of anthropomorphic robots is lacking. To fill this gap, we introduce the ABOT (Anthropomorphic roBOT) Database---a collection of 250+ images of real-world robots with one or more human-like appearance features (http://www.abotdatabase.info). Harnessing this database, our research has identified appearance dimensions that are most predictive of overall perceptions of robots' human-like appearance. We have also created an online estimation tool to help researchers predict how human-like a new robot will be perceived given the presence of various appearance features. The present research sheds new light on what makes a robot look human, and makes publicly accessible a powerful new tool for future research on robots' human-likeness.