Image forgery detection by semi-automatic wavelet soft-Thresholding with error level analysis

Jeronymo, Daniel Cavalcanti; Campbell, Yuri; Coelho, Leandro dos Santos

doi:10.1016/j.eswa.2017.05.044

Cited by 40 publications

(18 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Local noise residuals and camera characteristics [14] abnormal computer generated image color difference [12] Cpatel et al [15] proposed a method to identify the forgery region frames from a given input video by using EXIF image tag information and ELA. Jeronymo et al [16] presented a method for the detection of image forgery in lossy compressed digital images by using ELA and its noisy components were filtered with automatic wavelet soft-thresholding. Sudiatmika et al [17] proposed a new system from a combination ELA and CNN to solve the problem of distinguishing real images from forged ones.…”

Section: Consistency Of Imaging Equipmentmentioning

confidence: 99%

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

Zhang

Zhao

2020

Entropy

View full text Add to dashboard Cite

The quality and efficiency of generating face-swap images have been markedly strengthened by deep learning. For instance, the face-swap manipulations by DeepFake are so real that it is tricky to distinguish authenticity through automatic or manual detection. To augment the efficiency of distinguishing face-swap images generated by DeepFake from real facial ones, a novel counterfeit feature extraction technique was developed based on deep learning and error level analysis (ELA). It is related to entropy and information theory such as cross-entropy loss function in the final softmax layer. The DeepFake algorithm is only able to generate limited resolutions. Therefore, this algorithm results in two different image compression ratios between the fake face area as the foreground and the original area as the background, which would leave distinctive counterfeit traces. Through the ELA method, we can detect whether there are different image compression ratios. Convolution neural network (CNN), one of the representative technologies of deep learning, can extract the counterfeit feature and detect whether images are fake. Experiments show that the training efficiency of the CNN model can be significantly improved by the ELA method. In addition, the proposed technique can accurately extract the counterfeit feature, and therefore achieves outperformance in simplicity and efficiency compared with direct detection methods. Specifically, without loss of accuracy, the amount of computation can be significantly reduced (where the required floating-point computing power is reduced by more than 90%).

show abstract

Section: Consistency Of Imaging Equipmentmentioning

confidence: 99%

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

Zhang

Zhao

2020

Entropy

View full text Add to dashboard Cite

show abstract

“…En [42] utilizan la Transformada de Wavelet para filtrar los resultados de aplicar ELA con el objetivo de resaltar las alteraciones sobre la imagen.…”

Section: Iii-b Detección De Empalmeunclassified

Deteccion de Manipulaciones Copy-Move en Ficheros Multimedia mediante la Transformada Discreta del Coseno

Vega¹,

Orozco²,

Villalba³

2020

Seguridad Informática. X Congreso Iberoamericano, CIBSI 2020

View full text Add to dashboard Cite

“…Jeronymo et al [11] proposed an error level analysis for the detection of forgery in the digital images that seems to be lossy when compressed. The noise is removed automatically using the soft-thresholding.…”

Section: Thresholding-based Techniquesmentioning

confidence: 99%

“…The methods are cloning (copy-paste), splicing, erasing, and retouching. The splicing is the process of transferring a portion of the image into another image that can be done either through cut and paste operation or through the usage of other techniques such that there is a perfect match in the gradients of the target image [10,11]. The operation copy-paste is same as splicing, but the portion of the image is transferred within the image.…”

Section: Introductionmentioning

confidence: 99%

Illumination‐based texture descriptor and fruitfly support vector neural network for image forgery detection in face images

Cristin¹,

Ananth²,

Raj

2018

IET Image Processing

View full text Add to dashboard Cite

Image forgery detection by semi-automatic wavelet soft-Thresholding with error level analysis

Cited by 40 publications

References 32 publications

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

Deteccion de Manipulaciones Copy-Move en Ficheros Multimedia mediante la Transformada Discreta del Coseno

Illumination‐based texture descriptor and fruitfly support vector neural network for image forgery detection in face images

Contact Info

Product

Resources

About