MPEG-7 based dozen dimensional digital content architecture for semantic image retrieval services

Abstract

The rapid expansion of personal digital multimedia content in recent years requires a systematic indexing, categorizing and browsing interface to manage these enormous data. To tackle this crucial problem, the MPEG-7 standard was initiated with the intention to allow for efficient searching, indexing, filtering and accessing of multimedia content. We propose a MPEG-7 based multimedia content description tool which annotates multimedia data with twelve main attributes regarding its semantic representation. The twelve attributes include answers of who, what, when, where, why and how (5W1H) the digital content was produced as well as the respective direction, distance and duration (3D) information. We define digital multimedia contents including image, video and music embedded with the proposed semantic attributes as dozen dimensional digital content (DDDC). The establishment of DDDC would provide an interoperatable methodology for multimedia content management applications at semantic level. We also envision novel algorithms associate with DDDC attributes for semantic based content retrieval in the future.