Intelligent Digital Photo Management System Using Ontology and SWRL

The number of digital photos in the personal computer is exploding. Existing photo annotation and management systems suffer from some problems (some among them are quite serious), which discussed at the beginning of the full paper. Aiming at these problems, this paper proposed a solution based on ontology. First of all, the Family Album ontology is built to organize the domain knowledge and provide formal, explicit and conceptual annotation. Then we annotate preliminary semantic information for digital photos by automated extraction of semantic concepts from file titles, photo description texts, EXIF metadata and visual features of images etc.. Furthermore, the SWRL (Semantic Web Rule Language) rules are written and executed to extend previous semantic annotations and support knowledge inference. Finally, an Onto Album prototype system is developed for verifying the validity of the proposed approach. Experimental results show that the proposed approach is very effective and promising.