BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization

Wu, Yue; AbdAlmageed, Wael; Natarajan, Prem

doi:10.1007/978-3-030-01231-1_11

Cited by 220 publications

(248 citation statements)

References 35 publications

Supporting

Mentioning

247

Contrasting

Order By: Relevance

“…For training, all parameters were initialized using weights from a pre-trained model, which was taken from [20], the VGG16 on ImageNet for CNN Feature Extractor in Clone detection section. In addition, the Adam optimizer and binary cross entropy loss were used.…”

Section: Resultsmentioning

confidence: 99%

“…But, for the primary task, the Adam optimizer with categorical cross entropy loss was utilized. At the same time, precision, recall and F1 scores were collated in order to account the CMFD"s performance [20]. For the testing image, four values were computed: true positive (TP), true negative (TN), false positive (FP) and false negative (FN).…”

Section: Resultsmentioning

confidence: 99%

“…To achieve this, an end-to-end DNN should be created in such a way that it is capable of attaining distinct similar features of the tampered regions, wherein both the copied region and the source regions have more similarity than those of the other pristine regions. Consequently, as inspired by [20], a deep neural network was proposed with an architecture capable of distinguishing all types of tempered regions, which has undergone various transformations before forgery. The proposed DNN architecture is shown in Fig.…”

Section: Overviewmentioning

confidence: 99%

See 2 more Smart Citations

Copy-Move Forgery Detection in Digital Images using Neural Network

Patel*,

Bhatt

2020

IJITEE

View full text Add to dashboard Cite

Due to easy availability of image editing software applications, many of the digital images are tempered, either to hide some important facts of the image or just to enhance the image. Hence, the integrity of the image is compromised. Thus, in order to preserve the authenticity of an image, it is necessary to develop some algorithms to detect counterfeit parts of an image, if there is any. Two kinds of classic methods exist for the detection of forgery: the key- point based method in which major key points of the image is found and forged part is detected and the block based method that locates the forged part by sectioning the whole image into blocks. Unlike these two classic methods that require multiple stages, our proposed CNN solution provides better image forgery detection. Our experimental results revealed a better forgery detection performance than any other classic approaches.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Overviewmentioning

confidence: 99%

See 1 more Smart Citation

Copy-Move Forgery Detection in Digital Images using Neural Network

Patel*,

Bhatt

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…A new deep neural network is proposed by Yue Wu, et.al [2] where copied parts were detected successfully. In order to draw out the block like features a neural network was used.…”

Section: Literature Surveymentioning

confidence: 99%

Copy-Move Image Forgery Detection using Adhoc Algorithm

Prathyakshini*

2020

IJRTE

View full text Add to dashboard Cite

It is easy make fake images by making use of editing software. It has become an effortless job to put together or detach some attributes from an image. Validation of digital images is very essential. Identifying the fake image is the crucial topic. In order to identify tampered image active and passive detection methods are used. An image can be tampered by using image splicing, copy-move, and retouching. In particular, copy-move attack is considered in this paper. It is essential to find out whether the image is tampered or not. An effective method for detecting forged image is proposed which uses adhoc algorithm. In this algorithm there is no need of original image as it compares the similar pixels in the given image. Clusters which are larger than block size are pulled out. Similar clusters are extracted using some similarity function. The method successfully detects the forged parts in the image and saves the forged image in JPEG format. The performance is measured on various images.

show abstract

“…Detection of digital manipulations in images has been studied extensively in the past for image-splicing, copymove forgery, resampling and retouching of images at the pixel-level [3,28,29,30]. These methods work by either verifying embedded watermarks within images or analyzing pixel-level consistencies in search for artifacts.…”

Section: Related Workmentioning

confidence: 99%

AIRD: Adversarial Learning Framework for Image Repurposing Detection

Jaiswal¹,

Wu²,

AbdAlmageed³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

View full text Add to dashboard Cite

Image repurposing is a commonly used method for spreading misinformation on social media and online forums, which involves publishing untampered images with modified metadata to create rumors and further propaganda. While manual verification is possible, given vast amounts of verified knowledge available on the internet, the increasing prevalence and ease of this form of semantic manipulation call for the development of robust automatic ways of assessing the semantic integrity of multimedia data. In this paper, we present a novel method for image repurposing detection that is based on the real-world adversarial interplay between a bad actor who repurposes images with counterfeit metadata and a watchdog who verifies the semantic consistency between images and their accompanying metadata, where both players have access to a reference dataset of verified content, which they can use to achieve their goals. The proposed method exhibits state-of-the-art performance on location-identity, subject-identity and painting-artist verification, showing its efficacy across a diverse set of scenarios.

show abstract

BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization

Cited by 220 publications

References 35 publications

Copy-Move Forgery Detection in Digital Images using Neural Network

Copy-Move Forgery Detection in Digital Images using Neural Network

Copy-Move Image Forgery Detection using Adhoc Algorithm

AIRD: Adversarial Learning Framework for Image Repurposing Detection

Contact Info

Product

Resources

About