Semantic levels of domain-independent commonsense knowledgebase for visual indexing and retrieval applications

Building intelligent tools for searching, indexing and retrieval applications is needed to congregate the rapidly increasing amount of visual data. This raised the need for building and maintaining ontologies and knowledgebases to support textual semantic representation of visual contents, which is an important block in these applications. This paper proposes a commonsense knowledgebase that forms the link between the visual world and its semantic textual representation. This domain-independent knowledge is provided at different levels of semantics by a fully automated engine that analyses, fuses and integrates previous commonsense knowledgebases. This knowledgebase satisfies the levels of semantic by adding two new levels: temporal event scenarios and psycholinguistic understanding. Statistical properties and an experiment evaluation, show coherency and effectiveness of the proposed knowledgebase in providing the knowledge needed for wide-domain visual applications.