Along with the increase in the number of people using internet, the number of people sharing images across various web sites. One of the major issues with the sharing of images on public web sites is the unauthorized access of the content of the image. We propose a two-level framework which according to the user’s available history on the site, determines the best available privacy policy for the user’s images being uploaded.

We propose in this project non-recommended user can search and send the request of image to the administrator can accept the response and approve the access permissions.

A hierarchical image classification that classifies pictures initially based on their contents then refine every class into subcategories based mostly on their metadata. Such a hierarchical classification provides a higher priority to image content.