Content-based Image Retrieval by Exploring Bandletized Regions through Support Vector Machines

One of the major requirements of the Content Based Image Retrieval (CBIR) systems is to ensure the meaningful image retrieval against query images. CBIR systems provide potential solutions of retrieving semantically similar images from large image repositories against any query image. The performances of these systems severely degrade by the inclusion of image contents which do not comprise the objects of interest in an image during the image representation phase. Segmentation of the images is considered as a solution but there isn't any technique which can guarantee the object extraction in a robust way. Another limitation of the segmentation is that, most of the image segmentation techniques are very slow and still their results are not reliable. To overcome these problems a Bandelets transform based image representation technique is presented in this paper, which reliably returns the information about the major objects found in an image. For image retrieval purposes Support Vector Machine are applied and the performance of the system is evaluated on three standard data sets used in the domain of content based image retrieval.