Improving Web Image Search Re-Ranking Using Hybrid Approach

The explosive growth and widespread accessibility of community contributed media content on the Internet have led to a surge of research activity in image search. Approaches that apply text search techniques for image search have achieved limited success as they entirely ignore visual content as a ranking signal. We propose an adaptive visual similarity to re-rank the text based search results. A query image is first categorized as one of several predefined intention categories, and a specific similarity measure has been used inside each of category to combine the image features for re-ranking based on the query image.