Semantic ontology for annotated images

• Main Authors: Ullah, R., Said, A.B.M., Saleem, M.Q., Jaafar, J., Ullah, I.
• Format: Conference or Workshop Item
• Published: Institute of Electrical and Electronics Engineers Inc. 2016
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85010456955&doi=10.1109%2fICCOINS.2016.7783250&partnerID=40&md5=120ca485a201b25d6a25830246038da0; http://eprints.utp.edu.my/30462/

In multimedia search the retrieval of an image from a huge data-set are surrounded with extensive widespread concerns. Without procedures, the content of multimedia for semantic-interpretation is not clearly or really available for use. Manual Annotation is the only simple technique that helps to overcome semantic-interpretation. However, manual Annotation is not only time wasting and costly but also encompassed with the absence of concept diversity and semantic gap. This paper extends a semantic ontology method to extract label terms of the annotated image. LabelMe is the annotated data-set of the so far annotated terms. It enhances terms with the support of Knowledge bases of WordNet and ConceptNet, particularly. It supplements the identical synonyms as well as semantically related terms. It further reduces the semantic interpretation as well as increases the Semantic ontology for that annotated term domain. The results of an experiment performed shows that, the synonym terms were 15 and conceptually terms were 79 added along the primary list. It represents concept diversity an enhancement of 119.13 unique terms in the original list. © 2016 IEEE.