Paper Title
An Optimization Technique For Online Image Search Re-Ranking

Abstract
Abstract- Commercial search engines such as Bing and Google have adopted Image re-ranking as an effective way to improve the results of web-based image search. Given a query keyword, a pool of images are first retrieved based on textual information. It becomes difficult for user to interpret intention only on query keywords which leads to ambiguous results which are far different from user’s satisfaction. In this paper, we propose a novel Internet image search approach. The user is asked to select a query image from pool with minimum effort and images from a pool retrieved by text-based search are re- ranked based on both visual and textual content. This procedure of selecting the query image and then re-ranking requires four steps: A query image is first categorized into one of several predefined intention categories, and a specific similarity measure is used inside each category to combine image features for re-ranking based on the query image. Query keywords are expanded to capture user intention, through the visual content of the query image selected by the user and through image clustering. Image pool is enlarged to contain more relevant images. The query image is also expanded by using keyword expansion. All four of these steps are automatic with only one click in the first step without increasing user’s burden. This makes it possible for Internet scale image search by both textual and visual content with a very simple user interface.