Functionality-Based Web Image Categorization

Jianying Hu, Amit Bagga

Abstract: The World Wide Web provides an increasingly powerful and popular publication mechanism. Web documents often contain a large number of images serving various different purposes. Automatic identification of the functional categories of these images has important applications including information extraction, web mining, web page summarization and mobile access.  It is also a challenging task requiring a combination of sophisticated image understanding and text analysis techniques. In this paper we outline a first step towards automatic functionality-based image categorization: an algorithm for the identification of two of the most important image categories, namely story and preview images.