User-intent visual information ranking system

Nowadays, the rapid growth of World Wide Web has been resulted in an exponential growth of the data and visual information with full of interesting bits of contents that can be found online. In such situations, finding out images that satisfy user intentions from a huge collection is more and more required, which emphasizes the importance of web image search and visual information ranking system as filters for users. For these reasons, we propose user-centric visual information rank and re-ranking system for web image search to explore the global trends in innovation by combining the sharing patterns of social network. Specifically, we establish an embedded Markov Chain Model along with local and global image features of visual information content for ranking image search engine. In order to evaluate the performance of proposed method, we will conduct a series of experiments based on social media platforms and a real-life social Yelp network dataset with respect to consumer perspectives.