Reliability Map Estimation For CNN-Based Camera Model Attribution

TL;DR

This paper introduces a CNN-based method to estimate the reliability of camera model attribution on image patches, improving accuracy by guiding forgery localization and assessing image integrity.

Contribution

It proposes a novel CNN-based reliability map estimation technique that enhances camera model attribution accuracy on small image patches.

Findings

Reliability maps improve attribution accuracy by over 8%.

Method effectively identifies image regions with reliable camera traces.

Enhances forgery localization and image integrity assessment.

Abstract

Among the image forensic issues investigated in the last few years, great attention has been devoted to blind camera model attribution. This refers to the problem of detecting which camera model has been used to acquire an image by only exploiting pixel information. Solving this problem has great impact on image integrity assessment as well as on authenticity verification. Recent advancements that use convolutional neural networks (CNNs) in the media forensic field have enabled camera model attribution methods to work well even on small image patches. These improvements are also important for determining forgery localization. Some patches of an image may not contain enough information related to the camera model (e.g., saturated patches). In this paper, we propose a CNN-based solution to estimate the camera model attribution reliability of a given image patch. We show that we can estimate a reliability-map indicating which portions of the image contain reliable camera traces. Testing using a well known dataset confirms that by using this information, it is possible to increase small patch camera model attribution accuracy by more than 8% on a single patch.