In the last decade, epigraphists have begun to show a new interest in signacula, a kind of seals used to identify soldiers (as the modern “dog-tags”) or even civilian goods. Signacula are a class of artifacts for a long time neglected. This has brought numerous contributions devoted to the different regional contexts, along with reflections on methodological questions, not to mention the momentum towards the digitizing of a corpus which counts at least 3.500 pieces. These artifacts have a great potential in providing information related not only to the economy and to the administration of the “res” (i.e., public and private affairs, as Romans intended), but also about the profile of the signacula holders. In this scenario, the Sicilian context proved to be particularly significant due to the presence of several seal impressions on mortar in the Late Antique cemeteries of Siracusa: a unique example in Sicily and an extremely rare one in Italian archaeology. This inspired a specific research question: it is possible to identify unequivocally a signaculum through its impression? And then, what are the implications for archaeological research? The aim of this contribution is to establish a protocol for semi-automatic matching between 3D models of seals and 3D models of impressions. This survey may open the way to the creation of a virtual edition of signacula augmented with 3D models of both seals and prints. We believe could be particularly meaningful to embed a method of seals and prints comparison in a digital collection of this kind. Furthermore, a research agenda may include the design of a machine learning algorithm for matching of 3D meshes.