Content-based indexing of multimedia databases

Abstract

A content-based Indexing method (Contindex) for indexing multimedia object is proposed. A special neural-network model, called learning based on Experiences and Perspectives, is developed to create node categories by fusing multimodal feature measures. This model brings into the index the capability of self-organizing nodes with respect to certain context and frames of reference. An icon image is generated for each intermediate node to facilitate visual browsing. Algorithms are developed to support multimedia object archival and retrieval using contindex.