Improving the image search engine relevance and user experience is very important to figure out user image search goals. When a user will enter a query to search an image, he should be displayed with relevant images. In proposed work, browsing history session information, bookmark data and visual information with image tags of user click through images or user feedback images are extracted. The session history is stored as click through log and the images are stored separately. This history and clicked and downloaded images by user is considered as implicit guidance, so that the personalized results can be presented to the user. From the browsing history, the URLs are visited for getting user domain keywords. By using these keywords and tags of images, user query specific topic mapping and query mapping is done. The proposed method performs Naive Bayesian classification on user clicked images to group them into relevant concepts. This classifier is tested on the images obtained as a result of user submitted, so that the user interesting images or goal images can be displayed as a result. A label wise clustering is used to display goal image results. The system is mainly for retrieving images using text-based queries. The main aim of the proposed work is an efficient image retrieval system to facilitates image search through user queries and improve user satisfaction by returning images that have a high probability to be downloaded by the user.
Index Terms—Click through log, User Profiles, Goal images, Image search goals.