Content-based Web Image Search Engine Evaluation Using Arabic Text Queries

摘要

'Image search engines' means web-based services that gather and index images on the internet. Image searching is done by general search engines (SEs) and by some specialised SEs. In addition, there are few 'meta-search engines', which pass search queries to more than one SE and then return back the results. Research on content-based image retrieval was the focus of attention of many researchers during the last decade. The paper compares the performance of three image SEs for answering Arabic text queries. The paper also evaluates whether the query s language has an effect on the content-based images retrieved. This paper's research consists of two phases. In the first phase, 10 Arabic text queries were used and the first 10 images retrieved were tested for relevancy. Then we calculated precision ratios for each query. In the second phase, image features, such as colour and shape, were analysed and evaluated using the Euclidian distance. The results of the first phase indicated that Google has the best retrieval effectiveness. The second phase results showed that the image content was not similar for the relevant images retrieved for a specific query neither for the irrelevant images.