MULTI MODAL ONTOLOGY SEARCH FOR SEMANTIC IMAGE RETRIEVAL

Abstract

In this world of fast computing, automation plays an important role. In image retrieval technique automation is a great quest. Giving an image as a query and retrieving relevant images is a challenging research area. In this paper we are proposing a research of using Multi-Modality Ontology integration for image retrieval concept. The core strategy in multimodal information retrieval is the combination or fusion of different data modalities to expand and complement information. Here we use both visual and textual ontology contents to provide search functionalities. Both images and texts are complimentary information units as the human perspective will be different. So, the computational linguistic of images will lead to disambiguate text meaning when it is not quite clear in right sense of several words. That’s why the Multi-Modal information retrieval may lead to an improved operation of information retrieval system. If we go for automation we are in need of a fuzzy technique to predicate the result. So in this paper we using Support Vector Machine classifier to classify the image automatically by using the general feature such as color, texture and texton of an image , then by using this result we can create both feature and domain ontology for an particular image. Using this Multi-Modality Ontology we can refine our image searching system.