Hybrid Method for Online Web Image Ranking Using Query Specific Semantic Signatures

Image re-ranking, is an effective way to improve the results of web-based image search and has been adopted by current commercial search engines. Various methods like relevance feedback, context based image retrieval, query specific semantic signature has been proposed for giving better performance in web image re-ranking. However each of these methods has their own advantages and disadvantages. To overcome lacuna of the existing system we are proposing we propose log based image re-ranking. This paper provides the technical achievements in research area of the web image re-ranking and proposed log based relevance feedback method for online web image Re-ranking.