Image Forgery Localization via Block-Grained Analysis of JPEG Artifacts

By Tiziano Bianchi, Alessandro Piva. IEEE Transactions on Information Forensics and Security, 2012

467 citations recorded by the source corpus.

Subfields: Biophysics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/78f0f6f55cdbb65ab63cd4178f6e035bddaf7fbb

How researchers see this paper

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

In Biophysics

In Computer Vision and Pattern Recognition

Citations in the corpus

Splicebuster: A new blind image splicing detector (2015, methodology): “Therefore, several methods have been proposed, like [8], [9] or [10], which exploit the statistical distribution of such coefficients.”
Media Forensics and DeepFakes: An Overview (2020, background): “These artifacts change depending on whether the two compressions are spatially aligned or not, but suitable detection [74] and localization [75], [76] methods have been proposed for both cases.”
Image Forgery Localization via Fine-Grained Analysis of CFA Artifacts (2012, unknown): “The light is ﬁltered by the Color Filter Array (CFA) before reaching the sensor (CCD or CMOS), so that for each pixel only one particular color is gathered.”
Photo forensics from JPEG dimples (2017, methodology): “…(DCT) coefﬁcients are used to identify the recording camera manufacturer and model [2]–[4]; anomalies in the distribution of DCT coefﬁcients are used to reveal multiple JPEG compressions [5]–[7]; and artifacts introduced by the JPEG blocking are used to detected localized tampering [8]–[10].”
MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection (2021, unknown): “The differences are calculated by varied approaches, including media-format based compression artifacts [6], [7], physicsbased lighting inconsistency [8], [9], statistical modeling [10], local noise estimation [11], etc.”
Image Splicing Localization using a Multi-task Fully Convolutional Network (MFCN) (2017, methodology): “Most of these methods use features from one of two subgroups: JPEG quantization artifacts and JPEG compression grid discontinuities [23, 5, 6, 14, 22, 36, 25, 1, 4].”
Noiseprint: A CNN-Based Camera Model Fingerprint (2018, methodology): “Popular targets of such analyses are lens aberration [5]–[7], camera response function [8]–[10], color filter array (CFA) [11]–[13] or JPEG artifacts [14]–[16].”
Hybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries (2019, methodology): “5891 – – NADJPEG [13] 0 .”
Constrained Convolutional Neural Networks: A New Approach Towards General Purpose Image Manipulation Detection (2018, methodology): “This approach has been successful in detecting many types of image tampering such as resizing and resampling [2], [3], [4], [5], [6], median filtering [7], [8], [9], [10], contrast enhancement [11], [12], [13], [14], multiple JPEG compression [15], [16], [17], [18], etc.”
Towards Flexible Blind JPEG Artifacts Removal (2021, background): “The estimation of the first quantization table of JPEG images is also a challenging problem and studied in both aligned [16, 33, 44, 47] and non-aligned cases [5, 10, 45].”