Semantic Space Expansion and Refinement

The revolutionary developments in the digital technologies have indicated a requirement for technology, that systematizes the huge images dataset for easy search and retrieval. This yields an essential demand for developing highly effective retrieval systems. Recently, wide-ranging research efforts have been made in the field of annotated images. However, image Annotation can tag by one term, which cannot accurately describe its semantic meaning and is still an open issue. This paper presents Semantic Space Expansion, which magnifies the annotated terms of the image into synonyms as well as with conceptual terms, which covered a wide range of semantics. The synonym terms added from the open knowledge base such as, WordNet while conceptually terms added from the open common-scenes knowledge base of ConceptNet. Due to expansions some of the terms are relevant while some of them are irrelevant from knowledge bases. Semantic Expansion Refinement (SER) is designed to filters relevant terms from the expansion list. The result of the experiments showed successfully enhancement of annotated image terms through tagging ratio and degree of retrieval.