WebSeer: An Image Search Engine for the World Wide Web

Abstract

Because of the size of the World Wide Web and its inherent lack of structure, finding what one is looking for can be a challenge. PC-Meter's March, 1996, survey found that three of the five most visited Web sites were search engines. However, while Web pages typically contain both text and images, all the currently available search engines only index text. This paper describes WebSeer, a system for locating images on the Web. WebSeer uses image content in addition to associated text to index images, presenting the user with a selection that potentially fits her needs. 1 This work was supported in part by ONR contract N00014-93-1-0332 and NSF Grant No. IRI-9210763A01. 2 Introduction The explosive growth of the World Wide Web has proven to be a double-edged sword. While an immense amount of material is now easily accessible on the Web, locating specific information remains a difficult task. An inexperienced user may find it next to impossible to find the information she wants; even a...