Giving Meanings to WWWW Images

摘要

Images are increasingly being embedded in HTML documents on the WWW. Such documents over the WWW essentially provides a rich source of image collection from which users can query. Interestingly, the semantics of thee images are typically described by their surrounding text. Unfortunately, most WWW image search engines fail to exploit these image semantics and give rise to poor recall and precision performance. In this paper, we propose a novel image representation model called Weith ChainNet. Weigth ChainNet is based on lexical chian that represents the semantics of an image from its nearby text. A new formula, called list space model, for comprove the retrieval effectiveness, we also propose two relevance feedback mechanisms. We conducted an extensive performance study on a collection of 5000 images obtained fro mdocuments identified by more than 2000 UURLs. Our results show that oru models and methods outperform existing technique. Moreover, the relevant feedback mechanisms can lead to sigificantly better retrieval effectiveness.