Content based image retrieval in a web 3.0 environment

With the dramatic growth of Internet and multimedia applications, a virtually free worldwide digital distribution infrastructure has emerged. The concept of intelligent web or web 3.0 gives an opportunity to its users to share information in a way that could reach a broader audience and provide that audience with much deeper accessibility and interpretation of the information. Legacy image search systems which rely on the text annotations like keywords, and captions to retrieve images are not appropriate in web 3.0 architecture. Because these systems are unable to retrieve images which do not have this associated information. Also these systems suffers from the high cost of manual text annotations and linguistic problems as well while sharing and retrieving images. Therefore to handle these issues an image retrieval and management technique is presented in this paper which considers the actual image contents and do not rely on the associated metadata. Our content based image retrieval technique incorporates Genetic algorithms with support vector machines and user feedbacks for image retrieval purposes, and assures the effective retrieval and sharing of images by taking the users considerations into an account.