Multi-level Experience Retrieval for the Personal Lifelog Media System

Personal lifelog media system stores and retrieves userpsilas every day experiences in the form of multimedia data format. This system involves huge amount of data and requires a metadata database system to enable user to retrieve the desired media efficiently. This paper proposes a multi-level abstracted metadata DB design to retrieve every day experiences in various ways with a user-friendly web interface. The simulated performance with real lifelog media data shows that suggested multi-level metadata DB structure can retrieve experience media data around four times more efficient compared with usual single-level annotation-based metadata database in the sense of retrieval time.