Abstrakt

Survey Paper on Web Image Re-Ranking Using Semantic Signature

Bhakti P. Buche, V.S.Nandedkar

Image re-ranking, as an effective way to improve the results of web-based image search has been adopted by current commercial search engines.a query keyword, a pool of images are first retrieved by the search engine based on textual information. Asking the user to select a query image from the set the minus images are reranked based on their visual similarities with the query image.Query and Image based recommendation sorted by the method of re-ranking provides an accurate output of images based on the visual semantic signatures of the query image .In query based recommendation, keyword expansions help provide better results whereas in image recommendation, re-ranking based on priority of images accessed by other users provides moreaccurate results.At the online stage, images are re-rankedby comparing their semantic signatures obtained from thevisual semantic space specified by the query keyword.