The invention provides a robust method to control interactive media using gestures. A method to retrieve metadata information from a multimedia outlet device, wherein the method follows the steps: (1) extracting image hot spot areas in a current captured image using face detection, (2) detecting a human gesture directive in at least one image hot spot area using gesture recognition, (3) determining if the gesture directive matches a pre-assigned command to a rich interaction module, (4) sending a signal to a rich interaction module corresponding to the pre-assigned command detected, (5) extracting a media image hot spot area from electrical signals sent from the multimedia, (6) matching any detected human gestures in at least one image hot spot area using gesture recognition with a specific pixel on a device screen, and (7) retrieving information from metadata assigned to an area of pixels on the screen.