Image retrieval using radial moments

Abstract

Images have always been considered an effective medium for presenting visual data in many applications of industry and academia. With the development of technology, a large amount of images are being generated everyday. Therefore, managing and indexing of images become essential in order to retrieve similar images effectively. In conventional systems, images are generally indexed with textual annotations. However, as the database grows larger, the use of keywords based methods to retrieve a particular image becomes inefficient. Besides, skilled manual labor is required to annotate every single image with appropriate keywords. As a consequence, it becomes a time-consuming and tedious task. Even the human perception does not meet the images retrieved by keywords based system, which is not capable of representing image contents. To prevailon these limitations, content based image retrieval (CBIR) systems came into existence. In CBIR, the retrieval of images is based on their visual attributes/features such as color, texture, and shape. Among them low level shape attribute/feature provides a persuasive notion to object individuality, which meets human visual perception. Thus, in this thesis, we follow shape based retrieval of images. Nevertheless, image retrieval based on shape attribute remains a difficult task. Various shape representation and description techniques can be classified into two categories contour based and region based. Contour based descriptors are also termed as local descriptors, while the region based descriptors are known as global descriptors. It is to be mentioned here that radial moments fall into the category of global descriptors. In this thesis, radial moments are studied and analyzed broadly and their performance is evaluated on image retrieval system. It has been found that among other radial moments, Zernike moments (ZMs) establish their superiority in terms of image representation, description and image retrieval rate.