A Novel Fast Retrieval Algorithm for Huge Amounts of Data

With the rapid development of Internet, information explosively grows at a geometric rate. How to retrieve useful information from the vast amounts of multimedia information resources is a hot research topic. A multi-feature-based image retrieval system on the condition of extracted multi-feature has been carried out. PCA method was used for dimensionality reduction. Relevance feedback technique is used to get the connection of system and users, and adjust the values of the features according to the feedback of users, to raise the accuracy of image retrieval and satisfy the users´ need. The experiment shows that the proposed algorithm has better retrieval performance.