ABSTRACT
This chapter introduces the fundamental techniques for Content-based image retrieval, including feature extraction, relevance feedback, image annotation, and large-scale visual index and discusses automatic image annotation based on visual content. It focuses on general visual feature extraction techniques which can be used in a wide range of multimedia applications. The chapter explains some commonly used color features: color moment, color histogram, and color correlogram. Texture is one of the most important characteristics used in identifying objects or regions of interests in an image. Shape plays an important role in human visual perception, and has been widely used as a basic representation for a variety of computer vision tasks and CBIK systems. Local features, which are distinctive and invariant to many kinds of geometric and photo-metric transformations, are widely utilized in a large number of applications, for example object categorization, image retrieval, robust matching, and robot localization.
