Intent Search: Image Retrieval Based On Query Image

Web-scale image search engines (e.g., Google image search, Bing image search) mostly rely on surrounding text features. It is difficult for them to interpret users’ search intention only by query keywords and this leads to ambiguous and noisy search results which are far from satisfactory. It is important to use visual information in order to solve the ambiguity in text-based image retrieval. In this paper, we are implementing a novel Internet image search approach. It only requires the user to click on one query image with minimum effort and images from a pool retrieved by text-based search are re-ranked based on both visual and textual content. Our key contribution is to capture the users’ search intention from this one-click query image in following steps. In this system, the user first submits query keyword. A pool of images is retrieved by text-based search. Then the user is asked to select a query image from the image pool. Images in the pool are re-ranked based on their visual similarities to the query image and the similarities are computed using Euclidean distance method. A query-specific visual similarity metric and a query specific textual similarity metric are learned from the selected examples and used to rank images. These similarity metrics reflect users’ intention at a finer levelsince every query image has different metrics.​