A SURVEY ON DIFFERENT WEB IMAGE RE-RANKING TECHNIQUES

Today hundreds and millions of people use YouTube, Tudou, Face book like social networks. So users upload tremendous number of images on the web. Many people search and view images and videos on the web every second. There are many methods to search and retrieve the images and videos: content based search, text based search, visual search and re-ranking techniques. The content based search, is widely used in the past decades.In this method the user give some example images or videos and then similar images and videos are returned by querying a visual representation in a large scale database. In text based multimedia search completely relies on indexing the associated textual information of images, such as image tags, web page file names, and surrounding text. With textual information, well understood search techniques can be applied directly to image search. Web image re-ranking techniques leverages from content and text based search. So it becomes a popular web image re-ranking method. Image re-ranking is an effective way to improve the results of web based image search has been adopted by the current commercial search engines. Image re-ranking is important and effective for improving the performance of a text based image search. Image re-ranking is the most popular research area and recently several researches started on this area. Naturally this is not a complete survey on the entire web image re-ranking techniques. In this focuses some of the web image re-ranking methods.