The impact of number of query words on image search engines

Abstract

In this article, the impact of increasing number of query words on information retrieval effectiveness of image search engines is investigated. First of all, four popular search engines, namely Google, Yahoo, Msn, and Ask are selected. Then, forty queries are extracted from the list of Wordtracker and categorized in four groups as one-word, two-word, three-word and four-word queries. After every query is run on the selected image search engines and binary human relevance judgment is done on first twenty image items retrieved, the performance evaluation of image search engines are done in terms of precision and normalized recall. Overall, Google appears to be the best image search engine. The information retrieval effectiveness of image search engines decreases, when the number of query words increases. Therefore, image search engines still need to be improved. © 2007 IEEE.