Multimedia content has becomes increasingly pervasive, ranging from documents to audio content to videos. This can cause undesirable delays in the exchange, search and storage of multimedia records. It is important to develop systems that process, filter, search and organize this information so that useful information can be derived efficiently from the accessible exploding mass of information. In order to achieve this, an interoperable multimedia archive description scheme, such as MPEG-7, is necessary for the ongoing media standardization efforts. This technology provides a multimedia archive description scheme for interoperable multimedia content descriptions. The data structure established in this technology provides an efficient form for describing a collection of multimedia records to facilitate navigation through the variety of multimedia content available today.
Browsing and searching through large collections of multimedia content from different sources is tedious and time-consuming. The technology provides a data structure which relates records by similarity measures. The principle data structure in the multimedia archive description scheme is a cluster which can include feature space attributes, semantic attributes, media attributes and meta attributes of the records in the archive. Cluster relationships can then relate records to clusters or clusters to clusters. This computer readable storage system may provide more efficient exchange and distribution of multimedia documents.
The increased efficiency of the technology has been demonstrated with various content including digital images, internet web pages, digital audio files, etc.
Patent Issued (US 6,941,325)
Tech Ventures Reference: IR MS99/04/08D