Description: Our team of archaeologists, computer scientists, and digital humanists unites outstanding problems in art and archaeology and cutting-edge computer-vision research – an example of digital humanities par excellence – to automate the matching of stamped pottery sherds in order to reconstruct this lost yet immeasurably valuable Native American art form. Called the “SnowVision”, our web interface will enable individuals and institutions both to upload and store sherd images and to use our machine-learning based matching algorithms to identify the original stamped designs from which their fragments descend. SnowVision project will enrich sherd data for researchers while also creating a “virtual” place which centralizes a new, richer, collective knowledge about the diversity, evolution, and geographical reach of stamped pottery designs over time.