SOCRatES: A Database of Realistic Data for SOurce Camera REcognition on Smartphones

Galdi, Chiara; Hartung, Frank; Dugelay, Jean-Luc

doi:10.5220/0007403706480655

Cited by 31 publications

(22 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used two datasets: our NYUAD mixed media dataset (NYUAD-MMD) and the SOCRatES dataset [22], for validating our hypothesis. The NYUAD-MMD contains visual media from 78 smartphone cameras (19 brands, 62 models).…”

Section: Experimental Analysismentioning

confidence: 99%

See 1 more Smart Citation

Effect of Video Pixel-Binning on Source Attribution of Mixed Media

Taspinar

Mohanty

Memon³

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Photo Response Non-Uniformity (PRNU) noise obtained from images or videos is used as a camera fingerprint to attribute visual objects captured by a camera. The PRNU-based source attribution method, however, fails when there is misalignment between the fingerprint and the query object. One example of such a misalignment, which has been overlooked in the field, is caused by the in-camera resizing technique that a video may have been subjected to. This paper investigates the attribution of visual media in the context of matching a video query object to an image fingerprint or vice versa. Specifically this paper focuses on improving camera attribution performance by taking into account the effects of binning, a commonly used in-camera resizing technique applied to video. We experimentally show that the True Positive Rate (TPR) obtained when binning is considered is approximately 3% higher.

show abstract

Section: Experimental Analysismentioning

confidence: 99%

“…1200 frames) of each video to create a video FE. The SOCRatES dataset [22] contains 103 cameras, 54 of which have non-stabilized videos and images. NCC was used to determine potential alignments between two fingerprints and PCE for testing if they do indeed match.…”

Section: Experimental Analysismentioning

confidence: 99%

Effect of Video Pixel-Binning on Source Attribution of Mixed Media

Taspinar

Mohanty

Memon³

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Each dataset consists of a large number of high resolution images from multiple devices, either digital cameras or smartphone cameras. More recent datasets like the SOCRatES [18] and DAXING datasets [19] feature images from a vast number of source devices (103 smartphone cameras from SOCRatES and 90 smartphone cameras from DAXING dataset). Despite the images from these datasets show good diversity and heterogeneity in terms of contents, all the above mentioned datasets focus on SDR images only and the diversity in camera exposure parameter settings was not given adequate consideration during the construction of these datasets.…”

Section: Existing Public Image Datasetsmentioning

confidence: 99%

Warwick Image Forensics Dataset for Device Fingerprinting in Multimedia Forensics

Quan

Zhou

et al. 2020

2020 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

show abstract

“…Different from the previous published databases, SOCRatES [9] is collected by the smartphone owners themselves. As such, great heterogeneity and realness is introduced in the captured data.…”

Section: H Socratesmentioning

confidence: 99%

“…Recently, Galdi et al release a digital image and video database named as SOurce Camera REcognition on Smartphones (SOCRatES), which is specially designed for source camera recognition on smartphones. With 103 different devices, SOCRatES [9] is the source camera identification database that includes the highest number of different sensors. There are also some public databases available for video source identification and content forgery detection.…”

Section: Introductionmentioning

confidence: 99%

Daxing Smartphone Identification Dataset

et al. 2019

View full text Add to dashboard Cite

Over the past few years, the imaging device has changed from digital cameras to smartphone cameras. With the popularity of mobile Internet applications, there explode massive digital images and videos captured by such smartphones, which are nearly held one per person. Consequently, the capturing source of images/videos delivers valuable identity information for criminal investigations and critical forensic evidence. It is significant to address the source identification of smartphone images/videos. In this paper, we build a Daxing smartphone identification dataset, which collects images and videos from extensive smartphones of different brands, models and devices. Specifically, the dataset includes 43 400 images and 1,400 videos captured by 90 smartphones of 22 models belonging to 5 brands. For example, there are 23 smartphone devices for the iPhone 6S (Plus) model. To the best of our knowledge, Daxing dataset uses the largest amount of smartphones for image/video source identification compared with other related datasets, as well as the highest numbers of devices per model and captured images/videos. The dataset has been released as a free and open-source for scientific researchers and criminal investigators.

show abstract

SOCRatES: A Database of Realistic Data for SOurce Camera REcognition on Smartphones

Cited by 31 publications

References 10 publications

Effect of Video Pixel-Binning on Source Attribution of Mixed Media

Effect of Video Pixel-Binning on Source Attribution of Mixed Media

Warwick Image Forensics Dataset for Device Fingerprinting in Multimedia Forensics

Daxing Smartphone Identification Dataset

Contact Info

Product

Resources

About