Camera Model Identification Using Audio and Visual Content from Videos

TL;DR

This paper introduces a multimedia forensic framework that identifies device models using audio, visual, or combined content from videos, leveraging CNNs and fusion rules, with promising results and potential for further improvement.

Contribution

It proposes a novel CNN-based framework for device identification using multimodal audio-visual content and fusion strategies, advancing multimedia forensic techniques.

Findings

Independent audio and visual classification show promising results.

Fusion of modalities offers potential for improved classification performance.

Statistical significance testing validates the results.

Abstract

The identification of device brands and models plays a pivotal role in the realm of multimedia forensic applications. This paper presents a framework capable of identifying devices using audio, visual content, or a fusion of them. The fusion of visual and audio content occurs later by applying two fundamental fusion rules: the product and the sum. The device identification problem is tackled as a classification one by leveraging Convolutional Neural Networks. Experimental evaluation illustrates that the proposed framework exhibits promising classification performance when independently using audio or visual content. Furthermore, although the fusion results don't consistently surpass both individual modalities, they demonstrate promising potential for enhancing classification performance. Future research could refine the fusion process to improve classification performance in both modalities consistently. Finally, a statistical significance test is performed for a more in-depth study of the classification results.