Video Camera Identification from Sensor Pattern Noise with a Constrained ConvNet

TL;DR

This paper introduces a novel method for identifying source cameras from videos using a specialized constrained ConvNet that extracts camera-specific noise patterns from video frames, achieving high accuracy and robustness.

Contribution

It presents the first approach for device-level video camera identification using a constrained convolutional neural network with color processing capabilities.

Findings

Achieved up to 93.1% accuracy on benchmark data

Robust to WhatsApp and YouTube compression

First to address device-level video camera identification

Abstract

The identification of source cameras from videos, though it is a highly relevant forensic analysis topic, has been studied much less than its counterpart that uses images. In this work we propose a method to identify the source camera of a video based on camera specific noise patterns that we extract from video frames. For the extraction of noise pattern features, we propose an extended version of a constrained convolutional layer capable of processing color inputs. Our system is designed to classify individual video frames which are in turn combined by a majority vote to identify the source camera. We evaluated this approach on the benchmark VISION data set consisting of 1539 videos from 28 different cameras. To the best of our knowledge, this is the first work that addresses the challenge of video camera identification on a device level. The experiments show that our approach is very promising, achieving up to 93.1% accuracy while being robust to the WhatsApp and YouTube compression techniques. This work is part of the EU-funded project 4NSEEK focused on forensics against child sexual abuse.