State-of-the-art in Content-based Image and Video Retrieval State-of-the-art in Content-based Image and Video Retrieval

Contents Preface vii 1 Image Content Analysis and Description 1 Xenophon Zabulis, Stelios C. Orphanoudakis Preface Content-based image and video retrieval is concerned with retrieving images and video sequences on the basis of automatically derived features such as color, texture, and shape information that is present in the images. The need for efficient storage and retrieval of images is not new, but the increase in the number and size of digital image collections made the problems of image retrieval widely recognized. The shortcomings with traditional methods of indexing, often based on keywords, have led to the interest in retrieval on the basis of features that are automatically derived from the image content. The 1992 USA's NSF workshop on Visual Information Management Systems [1] was one of the events that gave this research area a push. The search for solutions is now an active area of research. The emergence of content-based image and video retrieval has brought together and broadened the extend of a number of disciplines, such as image [2]. The purpose of this seminar was to bring together people from the various fields in order to promote information exchange and interaction among researchers who are interested in various aspects of accessing the content of image and video data. The past decade has witnessed the development of the first few commercial systems. These are still very limited in their functionality. The user requirements on image features can vary considerably, but they can be classified into three levels of abstraction: primitive features such as color or textures, logical features such as the identity of objects, and abstract features such as meaning or significance of the image [3]. While most current systems operate on the lowest of these levels, the user demands higher levels.