الفهرس 
AcknowledgementOnly 14 pages are availabe for public view
 |  | from | 110 |  |  |
| | | from | 110 | | |
Abstract
With the grow of the internet and rapid advantage made in storage devices, non-standard data such as images and videos have grown significantly in size. Rich information is hidden in these data collections that are potentially useful in a wide range of applications and research. The conventional data mining process involves deriving novel and useful information from data. The process of discovering valuable information from image data termed image mining finds its sources in data mining, content-based image retrieval, and image understanding and computer vision.
Image description constitutes the initial basis for the image mining. The ability to develop an efficient and effective image description model has been a more and more interesting and challenging topic of research. An effective model must be able to capture domain-specific high-level semantics and support all image features, from primitive to abstract.
This thesis focuses on new key technologies for building an effective image description tool, namely transformation-based image description scheme. This scheme combines wavelet transform to contrast accurate data modeling, XML technology to implement a general storage system for any set of image (image schema), and ontology approach to produce an effective data managing tool in a unified framework. The aim is to achieve an image description tool that allows a high level of flexibility in describing images. Empirical studies with different image datasets are presented to show the effectiveness of the proposed system for image mining.