Enhancing Sensor Pattern Noise for Source Camera Identification

Liu, Beibei; Wei, Xingjie; Yan, Jeff

doi:10.1145/2756601.2756614

Cited by 5 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Noticeably, in [14] authors showed that the Peak-to-Correlation Energy (PCE) provides a significantly more robust feature compared to normalized correlation. The vast interest in this research field fostered the creation of reference image datasets specifically tailored for the evaluation of source identification [16], allowing a thorough comparison of different methods [17]. Recently, the authors of [18] addressed the problem of reducing the computational complexity of fingerprint matching, both in terms of time and memory, through the use of random projections to compress the fingerprints, at the price of a small reduction in matching accuracy.…”

Section: Digital Video Source Device Identification Based On Sensomentioning

confidence: 99%

Hybrid reference-based Video Source Identification

Iuliani

Fontani²,

Shullani

et al. 2019

Sensors

View full text Add to dashboard Cite

Millions of users share images and videos generated by mobile devices with different profiles on social media platforms. When publishing illegal content, they prefer to use anonymous profiles. Multimedia Forensics allows us to determine whether videos or images have been captured with the same device, and thus, possibly, by the same person. Currently, the most promising technology to achieve this task exploits unique traces left by the camera sensor into the visual content. However, image and video source identification are still treated separately from one another. This approach is limited and anachronistic, if we consider that most of the visual media are today acquired using smartphones that capture both images and videos. In this paper we overcome this limitation by exploring a new approach that synergistically exploits images and videos to study the device from which they both come. Indeed, we prove it is possible to identify the source of a digital video by exploiting a reference sensor pattern noise generated from still images taken by the same device. The proposed method provides performance comparable with or even better than the state-of-the-art, where a reference pattern is estimated from video frames. Finally, we show that this strategy is effective even in the case of in-camera digitally stabilized videos, where a non-stabilized reference is not available, thus solving the limitations of the current state-of-the-art. We also show how this approach allows us to link social media profiles containing images and videos captured by the same sensor.

show abstract

Section: Digital Video Source Device Identification Based On Sensomentioning

confidence: 99%

Hybrid reference-based Video Source Identification

Iuliani

Fontani²,

Shullani

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…The sensor pattern noise (SPN) based source camera identification technique has been also well established to solve the SCI problem. However, [Liu et al, 2015] did an extensive evaluation among various ways of enhancing the SPN. They identified which enhancing methods offer some insights into the behavior of SPN for SCI and they achieved a roughly 15% error rate.…”

Section: State Of the Artmentioning

confidence: 99%

Deep learning for source camera identification on mobile devices

Freire-Obregón

Narducci

Barra

et al. 2019

Pattern Recognition Letters

View full text Add to dashboard Cite

In the present paper, we propose a source camera identification (SCI) method for mobile devices based on deep learning. Recently, convolutional neural networks (CNNs) have shown a remarkable performance on several tasks such as image recognition, video analysis or natural language processing. A CNN consists on a set of layers where each layer is composed by a set of high pass filters which are applied all over the input image. This convolution process provides the unique ability to extract features automatically from data and to learn from those features. Our proposal describes a CNN architecture which is able to infer the noise pattern of mobile camera sensors (also known as camera fingerprint) with the aim at detecting and identifying not only the mobile device used to capture an image (with a 98% of accuracy), but also from which embedded camera the image was captured. More specifically, we provide an extensive analysis on the proposed architecture considering different configurations. The experiment has been carried out using the images captured from different mobile devices cameras (MICHE-I Dataset) and the obtained results have proved the robustness of the proposed method.

show abstract