Relevance feedback methods for logo and trademark image retrieval on the web

Abstract

Relevance feedback is the state-of-the-art approach for adjusting query results to the needs of the users. This work extends the existing framework of image retrieval with relevance feedback on the Web by incorporating text and image content into the search and feedback process. Some of the most powerful relevance feedback methods are implemented and tested on a fully automated Web retrieval system with more than 250,000 logo and trademark images. This evaluation demonstrates that term re-weighting based on text and image content is the most effective approach.