Automatic Web Image Annotation for Image Retrieval Systems

The number of images is growing in a rapid speed with the popularity of digital cameras and for enriching the visual aesthetics. WWW is becoming a large image library for browsing, and it is an important issue that how to retrieve the images accurately on the web. In this paper we sketch the architecture of an image retrieval system with image annotation. And we propose four methods to generate the annotation automatically for every image from its hosted web page, by analyzing the structural blocks, collecting anchor text of link structures, and gathering shared annotation with other images with the same visual signature.