An object-oriented approach for image processing and semantic query based on content

This paper presents a new method for image retrieval considering the information extracted from the image through the segmentation process and the semantic interpretation of this information. We constructed an image ontology for describing the image contents from the independent domain. Using a XML processor we translated the ontology from the XML format to a hierarchy of classes. The instances of the ontology together with the objects, corresponding to the low level features extracted from the images, are stored in an object oriented database. The object oriented native query system is used for the retrieval of the images from the database. Our technique, which combines the visual feature descriptors, has a good time complexity and the experimental results on the image datasets show that the performance of the method is robust. The experiments showed that the retrieval can be conducted with good results regardless of the area from where the images come.