Reliability Map Estimation For CNN-Based Camera Model Attribution
This work addresses the challenge of improving camera model attribution accuracy for image integrity and authenticity verification, particularly in forensic applications, though it is incremental as it builds on existing CNN methods.
The paper tackles the problem of estimating the reliability of camera model attribution for small image patches in forensic analysis, proposing a CNN-based method to generate a reliability map that identifies patches with sufficient camera traces, resulting in an over 8% increase in attribution accuracy on a single patch.
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.