Our project focuses on watermarks found in the music manuscripts of Franz Schubert. The endeavour incorporates thermography, machine learning and signal processing to produce digitized watermarks for databases and manuscript descriptions as well as to curtail the approximate dating of some undated autographs. By applying fingerprint recognition software to the acquired thermographic watermark images, a new method for automatic clustering will be established. MEI will be used as the system’s foundation for data presentation online and to guarantee long-term archiving and open source access. As MEI currently does not provide a best practice for encoding watermark information, a standardized form will be developed in collaboration with the community.