Blind source camera identification

By Mehdi Kharrazi, Husrev Taha Sencar, Nasir D. Memon. 2004 International Conference on Image Processing, 2004. ICIP '04., 2004

352 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ee4b366158f464fe472305d3cd44a1ceb9c5b118

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

Digital camera identification from sensor pattern noise (2006, methodology): “This approach, however, cannot solve the problem in its entirety unless all cameras either insert watermarks or embed secure hashes in their images.”
Digital Single Lens Reflex Camera Identification From Traces of Sensor Dust (2008, background): “For example, optical distortions due to a type of lens, the size of the imaging sensor, the choice of color filter array and corresponding demosaicing algorithm, and color-processing algorithms can be detected and quantitatively characterized by appropriate image-analysis techniques [3], [8]–[12].”
Detecting Image Splicing using Geometry Invariants and Camera Characteristics Consistency (2006, neutral): “Memon et al used cross color channel features to detect whether two images came from the same camera [4].”
Exposing digital forgeries in color filter array interpolated images (2005, neutral): “We believe that many complementary techniques such as that presented here, and those that we [5], [8]–[10] and others [4], [6], [7] develop, will be needed to reliably expose digital forgeries.”
Using decision fusion of feature selection in digital forensics for camera source model identification (2012, methodology): “[19] H Sensor imperfections * * N [24] S Color features, image quality metrics, wavelet”
The 'Dresden Image Database' for benchmarking digital image forensics (2010, methodology): “The cameras were drawn from only 25 di.erent models to ensure that device-speci.c and model-speci.c characteristics can be disentangled and studied separately, as validated with results in this paper.”
Digital image forgery detection using passive techniques: A survey (2013, methodology): “Kirchner (2008) implemented a resampling detection method based on cumulative periodograms. Variance of prediction residuals of a resampled signal can be used to describe periodic artifacts in the corresponding p-map. Mahdian and Saic (2008c) proposed a blind, efficient and automatic method capable ”
Digital image forensics: a booklet for beginners (2010, methodology): “[52] propose to use a set of image features to characterize a specific digital camera, assuming that the image can be affected by color processing and”
Determining Image Origin and Integrity Using Sensor Noise (2008, methodology): “We start by dividing the image into disjoint blocks and assume that, within each block , and are constant equal to and , respectively.3 Both quantities will be replaced with their estimated values , , obtained using a predictor (see Section V).”
Source Generator Attribution via Inversion (2019, background): “Whereas traditional image forensics already include powerful techniques applicable to images captured with a wide range of cameras [16, 12, 3, 4, 9], there are relatively fewer options available to forensic analysts operating on synthetic imagery.”