Source Camera Identification on Multi-Camera Phones

Abstract

Camera identification addresses the scenario where an investigator has a questioned digital image from an unknown camera. The investigator wants to know whether the questioned image was taken by a camera on a person of interest’s phone. Researchers discovered that slight imperfections in a camera’s sensor array can be used as an identifying feature or camera fingerprint in this scenario. These imperfections result from the manufacturing process and cause some pixels to produce consistently brighter or darker values than their neighboring pixels. A camera leaves its fingerprint in the images that it takes. A camera fingerprint is typically estimated from 50 or more reference images known to have been taken by the person of interest’s camera. A camera fingerprint is also estimated from the questioned image. Most camera identification methods measure the similarity between the two camera fingerprints with a similarity score such as correlation distance or peak-to-energy correlation. The score is then compared to a reference set of similarity scores to determine whether the questioned image originated from the POI’s camera. Previous camera identification methods have been tested on images taken by digital still cameras and the main rear cameras of mobile phones. Major smartphone brands now include a front (selfie) camera, and many offer additional rear cameras such as ultra-wide-angle and telephoto. This presentation will focus on camera identification for multi-camera phones and explore the distributions of similarity scores within (same camera) and between (different cameras) pairs of cameras on a small set of multi-camera phones.