Camera Model Identification with SPAIR-Swin and Entropy based Non-Homogeneous Patches
This work addresses image forensics for applications like authenticity verification and copyright protection, presenting an incremental improvement with novel components.
The paper tackles source camera model identification (SCMI) for image forensics by proposing SPAIR-Swin, a model combining a modified spatial attention mechanism with a Swin Transformer, and a patch selection strategy focusing on high-entropy regions, achieving patch-level accuracies up to 99.45% and image-level accuracies up to 100% on benchmark datasets.
Source camera model identification (SCMI) plays a pivotal role in image forensics with applications including authenticity verification and copyright protection. For identifying the camera model used to capture a given image, we propose SPAIR-Swin, a novel model combining a modified spatial attention mechanism and inverted residual block (SPAIR) with a Swin Transformer. SPAIR-Swin effectively captures both global and local features, enabling robust identification of artifacts such as noise patterns that are particularly effective for SCMI. Additionally, unlike conventional methods focusing on homogeneous patches, we propose a patch selection strategy for SCMI that emphasizes high-entropy regions rich in patterns and textures. Extensive evaluations on four benchmark SCMI datasets demonstrate that SPAIR-Swin outperforms existing methods, achieving patch-level accuracies of 99.45%, 98.39%, 99.45%, and 97.46% and image-level accuracies of 99.87%, 99.32%, 100%, and 98.61% on the Dresden, Vision, Forchheim, and Socrates datasets, respectively. Our findings highlight that high-entropy patches, which contain high-frequency information such as edge sharpness, noise, and compression artifacts, are more favorable in improving SCMI accuracy. Code will be made available upon request.