Camera Model Identification Using Convolutional Neural Networks

TL;DR

This paper presents a deep learning approach using CNNs for camera model identification, achieving high accuracy and robustness in a competitive Kaggle challenge.

Contribution

The work introduces a CNN-based method with aggressive data augmentation for camera model identification, achieving 98% accuracy and demonstrating robustness against transformations.

Findings

Achieved 98% accuracy on unseen data

Outperformed most competitors in the Kaggle challenge

Demonstrated robustness with data augmentation

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.