A Novel Hierarchical-Classification-Block Based Convolutional Neural Network for Source Camera Model Identification

TL;DR

This paper introduces a hierarchical classification system with classifier blocks for source camera model identification, reducing memory and training complexity while maintaining state-of-the-art accuracy.

Contribution

It proposes a novel classifier-block-level hierarchical approach that minimizes parameters and simplifies adding new camera models compared to traditional network-level systems.

Findings

Achieves state-of-the-art accuracy on Dresden dataset.

Uses fewer parameters than existing hierarchical models.

Maintains performance while reducing memory and training complexity.

Abstract

Digital security has been an active area of research interest due to the rapid adaptation of internet infrastructure, the increasing popularity of social media, and digital cameras. Due to inherent differences in working principles to generate an image, different camera brands left behind different intrinsic processing noises which can be used to identify the camera brand. In the last decade, many signal processing and deep learning-based methods have been proposed to identify and isolate this noise from the scene details in an image to detect the source camera brand. One prominent solution is to utilize a hierarchical classification system rather than the traditional single-classifier approach. Different individual networks are used for brand-level and model-level source camera identification. This approach allows for better scaling and requires minimal modifications for adding a new camera brand/model to the solution. However, using different full-fledged networks for both brand and model-level classification substantially increases memory consumption and training complexity. Moreover, extracted low-level features from the different network's initial layers often coincide, resulting in redundant weights. To mitigate the training and memory complexity, we propose a classifier-block-level hierarchical system instead of a network-level one for source camera model classification. Our proposed approach not only results in significantly fewer parameters but also retains the capability to add a new camera model with minimal modification. Thorough experimentation on the publicly available Dresden dataset shows that our proposed approach can achieve the same level of state-of-the-art performance but requires fewer parameters compared to a state-of-the-art network-level hierarchical-based system.