Abstract—The field of analyzing and understanding high-dimension real world data in a knowledgeable form is known as computer vision. Image is such a high dimension real world data which is enormously available in meaningless way. Using Ontologies in this computer vision field will enable a high end Ontology knowledge based image analysis and understanding. The main objective of this paper is to develop a frame work that creates a Bag of Visual Words for sports events using low level features of images and to develop ontology to provide semantic meaning to the images. Such semantically available images can be easily retrieved using a semantic image retrieval system. We used the concepts of enhanced Scale Invariant Feature Transform (SIFT) for feature extraction and Support Vector Machine based classification model to provide semantic to the images for action classification of images
Index Terms—Computer vision, ontology, bag of visual words, SIFT, SVM and knowledge-based component.
K. K. Thyagharajan is with RMD Engineering College, Kavaraipettai, India (e-mail: kkthyagharajan@yahoo.com).
G. Nagarajan is with Research Scholar of Sathyabama University, Chennai, India (e-mail: nagarajanme@yahoo.co.in).
[PDF]
Cite:K. K. Thyagharajan and G. Nagarajan, "Semantically Effective Visual Concept Illustration for Images," International Journal of Future Computer and Communication vol. 3, no. 2, pp. 124-128, 2014.