The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Image acquisition forensics: Forensic analysis to identify imaging source
Abstract
With widespread availability of digital images and easy-to-use image editing softwares, the origin and integrity of digital images has become a serious concern. This paper introduces the problem of image acquisition forensics and proposes a fusion of a set of signal processing features to identify the source of digital images. Our results show that the devices' color interpolation coefficients and noise statistics can jointly serve as good forensic features to help accurately trace the origin of the input image to its production process and to differentiate between images produced by cameras, cell phone cameras, scanners, and computer graphics. Further, the proposed features can also be extended to determining the brand and model of the device. Thus, the techniques introduced in this work provide a unified framework for image acquisition forensics.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Implementation of these algorithms across phones varies significantly [16], [17], is not typically lossless, and may not represent an optimal use of the available pixel information [18], further complicating attempts to quantify and compare images.”
From Quantitative Imaging with a Mobile Phone Microscope (2014) · cites this paper as [17]
Citations
Cites
Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines
Lyu, S., & Farid, H. (2003) · Lecture Notes in Computer Science · doi:10.1007/3-540-36415-3_22 · Cited by 450 · cited 2×
“In our experiments with [9], we employ the same set of cell phone camera images (with 90 for training and 10 for testing) and examine the identification accuracies as a function of JPEG quality factors.”
MethodNonintrusive component forensics of visual sensors using output images
Swaminathan, A., Wu, M., & Liu, K. J. R. (2007) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2006.890307 · Cited by 246 · cited 4×
“Therefore, in standalone cameras and cell phone cameras, only one color is obtained for each pixel and the remaining two colors for any given pixel are estimated through an interpolation process, which in most cases are unique to each model of camera [1].”
BackgroundMethodSelf-citationDetermining digital image origin using sensor imperfections
Lukas, J., Fridrich, J., & Goljan, M. (2005) · SPIE Proceedings · doi:10.1117/12.587105 · Cited by 175 · cited 1×
“Noise features obtained by studying sensor imperfections have been used to identify camera model and set [4] and further extended to distinguish between images produced from different scanners [5, 6].”
MethodScanner identification using sensor pattern noise
Khanna, N., Mikkilineni, A. K., Chiu, G. T. ‐., Allebach, J. P., & Delp, E. J. (2007) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.705837 · Cited by 94 · cited 1×
“Noise features obtained by studying sensor imperfections have been used to identify camera model and set [4] and further extended to distinguish between images produced from different scanners [5, 6].”
MethodColumbia Photographic Images and Photorealistic Computer Graphics Dataset
Ng, T.-T., Chang, S.-F., Hsu, J., & Pepeljugoski, M. (2005) · Cited by 93
Robust scanner identification based on noise features
Gou, H., Swaminathan, A. D., & Wu, M. H. (2007) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.704688 · Cited by 75 · cited 3×
“The mean and the variance of Δbi over all the pixels in the smooth regions form our third set of 12 statistical noise features [5].”
BackgroundMethodSelf-citationIMPROVEMENTS ON SOURCE CAMERA-MODEL IDENTIFICATION BASED ON CFA INTERPOLATION
Bayram, S., Sencar, H. T., & Memon, N. D. (2005) · Cited by 69
Camera/Mobile Phone Source Identification for Digital Forensics
Tsai, M.-J., Lai, C.-L., & Liu, J. (2007) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2007.366212 · Cited by 50 · cited 2×
“7% for five models, and this is significantly better than existing techniques that produce average accuracies close to 92% over four camera models from two different camera brands [3].”
BackgroundMethodForensic classification of imaging sensor types
Khanna, N., Mikkilineni, A. K., Chiu, G. T. ‐., Allebach, J. P., & Delp, E. J. (2007) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.705849 · Cited by 41 · cited 1×
“Recently, the work in [7] proposed a set of noise features for classifying images produced using different sensor types; however, their work is restricted to differentiating scanned and non-scanned camera images.”
Background
Cited by
An Overview on Image Forensics
Piva, A. (2013) · ISRN Signal Processing · doi:10.1155/2013/496701 · Cited by 426
“In [41] also, PRNU noise features and CFA interpolation coefficients are used jointly to estimate source type and camera model.”
MethodInfluentialInformation Forensics: An Overview of the First Decade
Stamm, M. C., Wu, M., & Liu, K. J. R. (2013) · IEEE Access · doi:10.1109/access.2013.2260814 · Cited by 394
“Combining such forensic features as noise statistics [95] and noise plus color interpolation features [96] with machine learning techniques, algorithms have been developed to determine the most likely type of imaging techniques or devices that was used to generate an image under question.”
MethodSelf-citationQuantitative Imaging with a Mobile Phone Microscope
Skandarajah, A., Reber, C. D., Switz, N. A., & Fletcher, D. A. (2014) · PLoS ONE · doi:10.1371/journal.pone.0096906 · Cited by 196
“Since the exact layout of the filter array is proprietary, as is the unique demosaicing algorithm used by each phone [17], we assume a common Bayer Filter Array directly on the sensor.”
BackgroundMethodSecurity in smart cities: A brief review of digital forensic schemes for biometric data
Ross, A., Banerjee, S., & Chowdhury, A. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.07.009 · Cited by 85
“It has applications in multi-media security as it can be used for copyright protection (attributing an image to a camera, and then associating the camera with its owner) [34] .”
BackgroundImage Origin Classification Based on Social Network Provenance
Caldelli, R., Becarelli, R., & Amerini, I. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2656842 · Cited by 77
Metadata
- Authors
- McKay, C., Swaminathan, A., Gou, H., & Wu, M.
- Affiliations
- University of Maryland, College Park (US)
- Venue
- 2008 IEEE International Conference on Acoustics, Speech and Signal Processing
- Publisher
- IEEE
- Published
- 2008-03
- Pages
- 1657-1660
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2149375453
- Cited by
- 62
- References
- 9
- Citations by year
- 2024: 1 · 2023: 3 · 2022: 3 · 2021: 2 · 2020: 3 · 2019: 2 · 2018: 3 · 2017: 5 · 2016: 2 · 2015: 4 · 2014: 7 · 2013: 6 · 2012: 3
- FWCI
- 4.81
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Keywords
- image forensics, image source identification, noise statistics, camera model identification, image integrity, image editing detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.