The 'Dresden Image Database'

The 'Dresden Image Database' bibliography

The aim of this webpage is to give an overview of publications that have made use of the 'Dresden Image Database'. For better classification, all papers have been assigned a number of keywords. A table with all keywords can be found below. We are happy to receive your comments if a paper is missing or keywords in the list of publications need adjustment. Just send an email to thomas.gloe (at) tu-dresden.de. The bibliography is also available as one single bibtex file: [url].

The bibliography was created as supplementary material to the following paper:

T. Gloe and R. BöhmeThe `Dresden Image Database' for Benchmarking Digital Image Forensics,  in Proceedings of the 25th Symposium On Applied Computing (ACM SAC 2010) vol.  2,   1585-15912010[abstract] [bibtex] [doi] [url]

You may also find Hany Farid's [url] and Andrew Lewis' [url] comprehensive bibliographies interesting, which cover digital image forensics in general.

(last update 2012-01-19 16:08:27 +0100)

Specify your search

Please enable javascript to sort the bibliography and to select authors or keywords.
sort by first authoryear
author
keywords image forensics  source identification  tamper detection  resampling detection  JPEG compression artefacts
show abstract
show bibtex

Literature

C.-H. Choi, J.-H. Choi, and H.-K. LeeCFA pattern identification of digital cameras using intermediate value counting,  in MM\&Sec'11, Proceedings of the 2011 ACM SIGMM Multimedia and Security Workshop21--262011[abstract] [bibtex] [doi] keywords: image forensics, source Identification, camera model identification

In digital image forensics, estimating the color filter array (CFA) pattern can be useful for digital camera identification. In this paper, we proposed the new method to estimate the CFA pattern of the digital cameras from a single image. Our method is based on the basic principal of CFA interpolation which fills an empty pixel using neighbor pixels. For each channel, we define the specific neighbor pattern and count the intermediate values. The CFA pattern is estimated by utilizing this counting information of three channels. The experimental results show that the proposed method achieves high accuracy with various camera models and CFA interpolation algorithms.

@inproceedings{Choi:2011aa,
author={Chang-Hee Choi and Jung-Ho Choi and Heung-Kyu Lee},
title={CFA pattern identification of digital cameras using intermediate value counting},
booktitle={{MM}\&{S}ec'11, {P}roceedings of the 2011 {ACM} {SIGMM} {M}ultimedia and {S}ecurity {W}orkshop},
pages={21--26},
year={2011},
publisher={{ACM}},
address={New York, NY, USA}}

Z. Deng, A. Gijsenij, and J. ZhangSource Camera Identification Using Auto-White Balance Approximation,  in 2011 IEEE International Conference on Computer Vision (ICCV)57--642011[abstract] [bibtex] [doi] keywords: image forensics, source Identification, camera model identification

Source camera identification finds many applications in real world. Although many identification methods have been proposed, they work with only a small set of cameras, and are weak at identifying cameras of the same model. Based on the observation that a digital image would not change if the same Auto-White Balance (AWB) algorithm is applied for the second time, this paper proposes to identify the source camera by approximating the AWB algorithm used inside the camera. To the best of our knowledge, this is the first time that a source camera identification method based on AWB has been reported. Experiments show near perfect accuracy in identifying cameras of different brands and models. Besides, proposed method performances quite well in distinguishing among camera devices of the same model, as AWB is done at the end of imaging pipeline, any small differences induced earlier will lead to different types of AWB output. Furthermore, the performance remains stable as the number of cameras grows large.

@inproceedings{Deng:2011aa,
author={Zhonghai Deng and Arjan Gijsenij and Jingyuan Zhang},
title={Source Camera Identification Using Auto-White Balance Approximation},
booktitle={2011 IEEE International Conference on Computer Vision (ICCV)},
pages={57--64},
year={2011}}

T. GloeFeature-Based Forensic Camera Model Identification,  in LNCS Transactions on Data Hiding and Multimedia Security (DHMMS) vol.  to appear,   2012[abstract] [bibtex] keywords: image forensics, camera model identification, source Identification

State-of-the-art digital forensic techniques for camera model identification draw attention on different sets of features to assign an image to the employed source model. This paper complements existing work, by a comprehensive evaluation of known feature sets employing a large set of 26 camera models with altogether 74 devices. We achieved the highest accuracies using the extended colour feature set and present several detail experiments to validate the ability of the features to separate between camera models and not between devices. Analysing more than 16,000 images, we present a comprehensive evaluation on 1) the number of required images and devices for training, 2) the influence of the number of camera models and camera settings on the detection results and 3) possibilities to handle unknown camera models when not all models coming into question are available or are even known. All experiments in this paper suggest: feature-based forensic camera model identification works in practice and provides reliable results even if only one device for each camera model under investigation is available to the forensic investigator.

@article{Gloe:2012aa,
author={Thomas Gloe},
title={Feature-Based Forensic Camera Model Identification},
journal={{LNCS} Transactions on Data Hiding and Multimedia Security (DHMMS)},
volume={to appear},
year={2012}}

T. Gloe and R. BöhmeThe `Dresden Image Database' for Benchmarking Digital Image Forensics,  in Proceedings of the 25th Symposium On Applied Computing (ACM SAC 2010) vol.  2,   1585--15912010[abstract] [bibtex] [doi] [url] keywords: image forensics, source identification

This paper introduces and documents a novel image database specifically built for the purpose of development and benchmarking of camera-based digital forensic techniques. More than 14,000 images of various indoor and outdoor scenes have been acquired under controlled and thus widely comparable conditions from altogether 73 digital cameras. The cameras were drawn from only 25 different models to ensure that device-specific and model-specific characteristics can be disentangled and studied separately, as validated with results in this paper. In addition, auxiliary images for the estimation of device-specific sensor noise pattern were collected for each camera. Another subset of images to study model-specific JPEG compression algorithms has been compiled for each model. The \lq Dresden Image Database\rq\ will be made freely available for scientific purposes when this accompanying paper is presented. The database is intended to become a useful resource for researchers and forensic investigators. Using a standard database as a benchmark not only makes results more comparable and reproducible, but it is also more economical and avoids potential copyright and privacy issues that go along with self-sampled benchmark sets from public photo communities on the Internet.

@inproceedings{Gloe:2010aa,
author={Thomas Gloe and Rainer Böhme},
title={The `{D}resden {I}mage {D}atabase' for Benchmarking Digital Image Forensics},
booktitle={Proceedings of the 25th Symposium On Applied Computing (ACM SAC 2010)},
pages={1585--1591},
volume={2},
year={2010}}

T. Gloe, K. Borowka, and A. WinklerEfficient estimation and large-scale evaluation of lateral chromatic aberration for digital image forensics,  in Proceedings of SPIE: Media Forensics and Security II,  Eds. N. D. Memon, J. Dittmann, A. M. Alattar, and E. J. Delp vol.  7541,   7541-72010[abstract] [bibtex] [doi] keywords: image forensics, source identification, tamper detection

The analysis of lateral chromatic aberration forms another ingredient for a well equipped toolbox of an image forensic investigator. Previous work proposed its application to forgery detection and image source identification. This paper takes a closer look on the current state-of-the-art method to analyse lateral chromatic aberration and presents a new approach to estimate lateral chromatic aberration in a runtime-efficient way. Employing a set of 11 different camera models including 43 devices, the characteristic of lateral chromatic aberration is investigated in a large-scale. The reported results point to general difficulties that have to be considered in real world investigations.

@inproceedings{Gloe:2010ab,
author={Thomas Gloe and Karsten Borowka and Antje Winkler},
title={Efficient estimation and large-scale evaluation of lateral chromatic aberration for digital image forensics},
booktitle={Proceedings of {SPIE}: Media Forensics and Security {II}},
editor={Nasir D. Memon and Jana Dittmann and Adnan M. Alattar and Edward J. Delp},
pages={7541-7},
volume={7541},
year={2010}}

T. Gloe, K. Borowka, and A. WinklerFeature-Based Camera Model Identification Works in Practice -- Results of a Comprehensive Evaluation Study,  in 11th Information Hiding, Darmstadt, Germany, June 8-10, 2009, Revised Selected Papers,  Eds. S. Katzenbeisser and A.-R. Sadeghi LNCS 5806,   262--2762009[abstract] [bibtex] [doi] keywords: image forensics, source identification

Feature-based camera model identification plays an important role in the toolbox for image source identification. It enables the forensic investigator to discover the probable source model employed to acquire an image under investigation. However, little is known about the performance on large sets of cameras that include multiple devices of the same model. Following the process of a forensic investigation, this paper tackles important questions for the application of feature-based camera model identification in real world scenarios. More than 9,000 images were acquired under controlled conditions using 44 digital cameras of 12 different models. This forms the basis for an in-depth analysis of a) intra-camera model similarity, b) the number of required devices and images for training the identification method, and c) the influence of camera settings. All experiments in this paper suggest: feature-based camera model identification works in practice and provides reliable results even if only one device for each camera model under investigation is available to the forensic investigator.

@inproceedings{Gloe:2009ab,
author={Thomas Gloe and Karsten Borowka and Antje Winkler},
title={Feature-Based Camera Model Identification Works in Practice -- Results of a Comprehensive Evaluation Study},
booktitle={11th Information Hiding, Darmstadt, Germany, June 8-10, 2009, Revised Selected Papers},
editor={Stefan Katzenbeisser and Ahmad-Reza Sadeghi},
pages={262--276},
volume={5806},
year={2009},
publisher={Springer-Verlag},
series={LNCS},
address={Berlin, Heidelberg}}

M. KirchnerEfficient estimation of CFA pattern configuration in digital camera images,  in Proceedings of SPIE: Media Forensics and Security II,  Eds. N. D. Memon, J. Dittmann, A. M. Alattar, and E. J. Delp vol.  7541,   7541112010[abstract] [bibtex] [doi] [url] keywords: image forensics, source identification

This paper proposes an efficient method to determine the concrete configuration of the color filter array (CFA) from demosaiced images. This is useful to decrease the degrees of freedom when checking for the existence or consistency of CFA artifacts in typical digital camera images. We see applications in a wide range of multimedia security scenarios whenever inter-pixel correlation plays an important role. Our method is based on a CFA synthesis procedure that finds the most likely raw sensor output for a given full-color image. We present approximate solutions that require only one linear filtering operation per image. The effectiveness of our method is demonstrated by experimental results from a large database of images.

@inproceedings{Kirchner:2010aa,
author={Matthias Kirchner},
title={Efficient estimation of {CFA} pattern configuration in digital camera images},
booktitle={Proceedings of {SPIE}: Media Forensics and Security {II}},
editor={Nasir D. Memon and Jana Dittmann and Adnan M. Alattar and Edward J. Delp},
pages={754111},
volume={7541},
year={2010}}

M. KirchnerLinear row and column predictors for the analysis of resized images,  in MM\&Sec'10, Proceedings of the 2010 ACM SIGMM Multimedia and Security Workshop13--182010[abstract] [bibtex] [doi] keywords: image forensics, tamper detection, resampling detection

This paper adds a new perspective to the analysis and detection of periodic interpolation artifacts in resized digital images. Instead of relying on a single, global predictor, we discuss how the specific structure of resized images can be explicitly modeled by a series of linear predictors. Characteristic periodic correlations between neighboring pixels are then measured in the estimated predictor coefficients itself. Experimental results on a large database of images suggest a superior detection performance compared to state-of-the-art methods.

@inproceedings{Kirchner:2010ab,
author={Matthias Kirchner},
title={Linear row and column predictors for the analysis of resized images},
booktitle={{MM}\&{S}ec'10, {P}roceedings of the 2010 {ACM} {SIGMM} {M}ultimedia and {S}ecurity {W}orkshop},
pages={13--18},
year={2010},
publisher={ACM},
address={New York, NY, USA}}

T. Gloe and R. BöhmeThe Dresden Image Database for Benchmarking Digital Image Forensics,  in Journal of Digital Forensic Practice vol.  3,   150--1592010[abstract] [bibtex] [doi] keywords: image forensics, source identification

This article introduces and documents a novel image database specifically built for the purpose of development and benchmarking of camera-based digital forensic techniques. More than 14,000 images of various indoor and outdoor scenes have been acquired under controlled and thus widely comparable conditions from altogether 73 digital cameras. The cameras were drawn from only 25 different models to ensure that device-specific and model-specific characteristics can be disentangled and studied separately, as validated with results in this paper. In addition, auxiliary images for the estimation of device-specific sensor noise pattern were collected for each camera. Another subset of images to study model-specific JPEG compression algorithms has been compiled for each model. The \lq Dresden Image Database\rq\ will be made freely available for scientific purposes when this accompanying paper is presented. The database is intended to become a useful resource for researchers and forensic investigators. Using a standard database as a benchmark not only makes results more comparable and reproducible, but it is also more economical and avoids potential copyright and privacy issues that go along with self-sampled benchmark sets from public photo communities on the Internet.

@article{Gloe:2010ac,
author={Thomas Gloe and Rainer Böhme},
title={The {D}resden Image Database for Benchmarking Digital Image Forensics},
journal={Journal of Digital Forensic Practice},
pages={150--159},
volume={3},
year={2010}}

M. Kirchner and T. GloeOn Resampling Detection in Re-Compressed Images,  in First IEEE International Workshop on Information Forensics and Security (WIFS '09)21--252009[abstract] [bibtex] [doi] [url] keywords: image forensics, tamper detection, resampling detection

Resampling detection has become a standard tool in digital image forensics. This paper investigates the important case of resampling detection in re-compressed JPEG images. We show how blocking artifacts of the previous compression step can help to increase the otherwise drastically reduced detection performance in JPEG compressed images. We give a formulation on how affine transformations of JPEG compressed images affect state-of-the-art resampling detectors and derive a new efficient detection variant, which better suits this relevant detection scenario. The principal appropriateness of using JPEG pre-compression artifacts for the detection of resampling in re-compressed images is backed with experimental evidence on a large image set and for a variety of different JPEG qualities.

@inproceedings{Kirchner:2009aa,
author={Matthias Kirchner and Thomas Gloe},
title={On Resampling Detection in Re-Compressed Images},
booktitle={First {IEEE} International Workshop on Information Forensics and Security (WIFS '09)},
pages={21--25},
year={2009}}

T. GloeDemystifying histograms of multi-quantised DCT coefficients,  in 2011 IEEE International Conference on Multimedia and EXPO (ICME 2011)2011[abstract] [bibtex] [doi] keywords: image forensics, JPEG compression artefacts

JPEG compression artefacts are among the most prominent features in the forensic analysis of digital images. Here, we focus on the spectral analysis of histograms of single- and multi-quantised DCT coefficients. We present a model of the frequency response of finite-support histograms, which explains position and magnitude of characteristic quantisation peaks with reasonable precision and gives valuable insights into the formation of quantisation artefacts in general. We derive a set of practical rules for the efficient analysis of single- and multi-compressed images and discuss applications in the estimation of quantisation tables.

@inproceedings{Gloe:2011aa,
author={Thomas Gloe},
title={Demystifying histograms of multi-quantised {DCT} coefficients},
booktitle={2011 {IEEE} International Conference on Multimedia and {EXPO} ({ICME} 2011)},
year={2011}}