Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis

By Zhouchen Lin, Junfeng He, Xiaoou Tang, Chi-Keung Tang. Pattern Recognition, 2009

430 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dda6489e35776271579bc93dc618b7e47c776e2b

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

Hybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries (2019, methodology): “Some of the tamper localization techniques include DCT Histograms [52], ADJPEG [13], NADJPEG [13], PatchMatch [24], Error level analysis [57], Block Features [49], and Noise Inconsistencies [60].”
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].”
Digital image forgery detection using passive techniques: A survey (2013, methodology): “Lukas (2000) implemented a technique to detect manipulation in digital images using the convolutional filtering and spectral filtering operations.”
Image Forgery Localization via Fine-Grained Analysis of CFA Artifacts (2012, neutral): “During the image life cycle, there are two main phases in which interpolation is applied: • Acquisition processing, to obtain the 3 color channels (red, green, and blue).”
Digital image forensics: a booklet for beginners (2010, methodology): “Popescu’s study is also the basis on which Lin and others [61] design their method for tampering localization, analyzing to what extent DCT coefficients randomize the double quantization effect.”
MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection (2021, neutral): “The differences are calculated by varied approaches, including media-format based compression artifacts [6], [7], physics-based lighting inconsistency [8], [9], statistical modeling [10], local noise estimation [11], etc.”
Media Forensics and DeepFakes: An Overview (2020, methodology): “Several BAG-based methods have been proposed in the literature [77]–[79], some of which even”
Image Forgery Localization via Block-Grained Analysis of JPEG Artifacts (2012, methodology): “This is the same scenario considered in [7].”
An Evaluation of Digital Image Forgery Detection Approaches (2017, methodology): “Lin et al. [19] proposed an automatic and quick altered JPEG image detection technique using analysis of DCT coefﬁcient in 2009.”
Noiseprint: A CNN-Based Camera Model Fingerprint (2018, background): “They can be roughly classified in three classes according to the features they exploit: i) JPEG artifacts [60], [61], [62], [63], [16], [64], ii) CFA artifacts [14], [13], iii) inconsistencies in the spatial distribution of features [65], [26], [66], [27], [28], [58].”