Camera-based Image Forgery Localization using Convolutional Neural Networks

TL;DR

This paper introduces a CNN-based noiseprint method for camera model fingerprinting that improves image forgery localization by reducing scene content interference compared to traditional PRNU-based techniques.

Contribution

It proposes a novel CNN-trained noiseprint approach that enhances forgery detection accuracy by focusing on camera model artifacts rather than device-specific noise.

Findings

Noiseprint-based method outperforms PRNU-based methods in localization accuracy

The approach is less affected by high-level scene content residuals

Experimental results demonstrate improved forgery localization performance

Abstract

Camera fingerprints are precious tools for a number of image forensics tasks. A well-known example is the photo response non-uniformity (PRNU) noise pattern, a powerful device fingerprint. Here, to address the image forgery localization problem, we rely on noiseprint, a recently proposed CNN-based camera model fingerprint. The CNN is trained to minimize the distance between same-model patches, and maximize the distance otherwise. As a result, the noiseprint accounts for model-related artifacts just like the PRNU accounts for device-related non-uniformities. However, unlike the PRNU, it is only mildly affected by residuals of high-level scene content. The experiments show that the proposed noiseprint-based forgery localization method improves over the PRNU-based reference.