PDC-ViT : Source Camera Identification using Pixel Difference Convolution and Vision Transformer

2025-01-27

AI Summary

To address insufficient accuracy in camera source identification for digital forensics of images and videos, this paper proposes an end-to-end deep learning method grounded in physical-layer pixel-differential representation. The core contribution is the first integration of sensor-pattern features—extracted via angular and radial pixel-difference convolutions (APDC/RPDC)—directly into a Vision Transformer (ViT) architecture, bypassing conventional patch-based inputs to explicitly model low-level hardware fingerprints. Evaluated on five benchmark datasets—Vision, Daxing, Socrates, QUFVD, and one additional standard dataset—the method achieves recognition accuracies of 94.30%, 84.00%, 94.22%, and 92.29%, respectively, consistently outperforming state-of-the-art approaches. This framework delivers high robustness and strong interpretability, providing a reliable technical foundation for multimedia provenance analysis in criminal investigation and counter-terrorism applications.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Security and Privacy: Data transparency and provenance
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Source camera identification has emerged as a vital solution to unlock incidents involving critical cases like terrorism, violence, and other criminal activities. The ability to trace the origin of an image/video can aid law enforcement agencies in gathering evidence and constructing the timeline of events. Moreover, identifying the owner of a certain device narrows down the area of search in a criminal investigation where smartphone devices are involved. This paper proposes a new pixel-based method for source camera identification, integrating Pixel Difference Convolution (PDC) with a Vision Transformer network (ViT), and named PDC-ViT. While the PDC acts as the backbone for feature extraction by exploiting Angular PDC (APDC) and Radial PDC (RPDC). These techniques enhance the capability to capture subtle variations in pixel information, which are crucial for distinguishing between different source cameras. The second part of the methodology focuses on classification, which is based on a Vision Transformer network. Unlike traditional methods that utilize image patches directly for training the classification network, the proposed approach uniquely inputs PDC features into the Vision Transformer network. To demonstrate the effectiveness of the PDC-ViT approach, it has been assessed on five different datasets, which include various image contents and video scenes. The method has also been compared with state-of-the-art source camera identification methods. Experimental results demonstrate the effectiveness and superiority of the proposed system in terms of accuracy and robustness when compared to its competitors. For example, our proposed PDC-ViT has achieved an accuracy of 94.30%, 84%, 94.22% and 92.29% using the Vision dataset, Daxing dataset, Socrates dataset and QUFVD dataset, respectively.

Problem

• Camera Source Identification
• Image and Video Analysis
• Forensic Investigation

Innovation

• PDC-ViT
• PDC feature extraction
• Visual Transformer (ViT)