The 'Dresden Image Database' for benchmarking digital image forensics

By Thomas Gloe, Rainer Böhme. ACM Symposium on Applied Computing, 2010

693 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a6859f695e6b2bd967df7cdb8becf8c9465b472a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Media Forensics and DeepFakes: An Overview (2020, background): “The Dresden image database [223] is the most popular one.”
Hybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries (2019, methodology): “Finally, these objects are used to create manipulation from the images of DRESDEN [33] and NIST’16 [2].”
Digital image forensics: a booklet for beginners (2010, methodology): “Few efforts in this direction [38, 71] have been already done; however, a large dataset comprehensive of different scenes, illumination and environmental conditions and attacks is still missing for, e.”
PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization (2021, methodology): “We follow the same processes above but randomly select donor and target images in KCMI [70], VISION [71], and Dresden [72] that are commonly used to identify camera source [20], to generate additional spliced images as supplementary.”
CoMoFoD — New database for copy-move forgery detection (2013, methodology): “Dresden Image Database [5] was developed for purpose of camera identification, and Goljan et al.”
Noiseprint: A CNN-Based Camera Model Fingerprint (2018, background): “• 44 cameras from the Dresden dataset [69], • 32 from Socrates dataset [70], • 32 from VISION [71], • 17 from our private dataset,”
RAISE: a raw images dataset for digital image forensics (2015, background): “Diﬀerently from other existing datasets targeting a speciﬁc forensic task (like splicing [12] and copy-move detection [1, 3] or source identiﬁcation [10]) where the images are processed accordingly, RAISE is conceived for a general purpose within the image forensics ﬁeld, since raw images contain…”
FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces (2018, positive): “Most notably, the “Dresden image database” consists of 14,000 images from 73 cameras, and is used primarily for camera ﬁngerprinting [45].”
Constrained Convolutional Neural Networks: A New Approach Towards General Purpose Image Manipulation Detection (2018, methodology): “Given the limited number of images in the 1st IEEE IFS-TC image forensics challenge database, we used the Dresden Image Database [46] to build our training and testing data.”
ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features (2019, methodology): “For manipulation trace feature , we use the Dresden Image Database [24] for pristine base images.”
MFC Datasets: Large-Scale Benchmark Datasets for Media Forensic Challenge Evaluation (2019, methodology): “The Dresden image database (2010) [43] contains 14,000 high resolution images from 73 digital cameras covering 25 camera models.”
SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization (2020, methodology): “module. We adopt the pre-trained feature extractor as proposed in [37]. The feature extraction network is trained on synthesized data generated based on images sampled from the Dresden Image Database [12], using classication supervision against 385-type image manipulation data. The feature extractor”