Camera Model Identification Using Convolutional Neural Networks

2018/10/06 by A. A. Kuzin, Kuzin, Artur, Artur Fattakhov +7
Computer Science · #Advanced Steganography and Watermarking Techniques #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1810.02981

openalex publication_date 2018/10/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Source camera identification is the process of determining which camera or model has been used to capture an image. In the recent years, there has been a rapid growth of research interest in the domain of forensics. In the current work, we describe our Deep Learning approach to the camera detection task of 10 cameras as a part of the Camera Model Identification Challenge hosted by Kaggle.com where our team finished 2nd out of 582 teams with the accuracy on the unseen data of 98%. We used aggressive data augmentations that allowed a model to stay robust against transformations. A number of experiments are carried out on datasets collected by organizers and scraped from the web.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• TernausNetV2: Fully Convolutional Network for Instance Segmentation

Related

• RemNet: Remnant Convolutional Neural Network for Camera Model\n Identification
• Application of DenseNet in Camera Model Identification and Post-processing Detection
• Digital Image Forensics using Deep Learning
• A Novel Hierarchical-Classification-Block Based Convolutional Neural Network for Source Camera Model Identification
• Evaluating Deep Learning and Traditional Approaches Used in Source Camera Identification