Camera identification with deep convolutional networks.

The possibility of detecting which camera has been used to shoot a specific picture is of paramount importance for many forensics tasks. This is extremely useful for copyright infringement cases, ownership attribution, as well as for detecting the authors of distributed illicit material (e.g., pedo-pornographic shots). Due to its importance, the forensics community has developed a series of robust detectors that exploit characteristic traces left by each camera on the acquired images during the acquisition pipeline. These traces are reverse-engineered in order to attribute a picture to a camera. In this paper, we investigate an alternative approach to solve camera identification problem. Indeed, we propose a data-driven algorithm based on convolutional neural networks, which learns features characterizing each camera directly from the acquired pictures. The proposed approach is tested on both instance-attribution and model-attribution, providing an accuracy greater than 94% in discriminating 27 camera models.