A knowledge based architecture for the virtual restoration of ancient photos

Historical images are essential documents of the recent past. Nevertheless, time and bad preservationcorrupt their physical supports. Digitization can be the solution to extend their “lives”, and digital techniquescan be used to recover lost information. This task is often difficult and time-consuming, if commercialrestoration tools are used for the purpose. A new solution is proposed to help non-expert usersin restoring their damaged photos. First, we defined a dual taxonomy for the defects in printed and digitizedphotos. We represented our restoration domain with an ontology and we created some rules tosuggest actions to perform in case of some specific events. Classes and properties of the ontology areincluded into a knowledge base, that grows dynamically with its use. A prototypal tool and a web applicationversion have been implemented as an interface to the database, and to support non-expert usersin the restoration process.