Image splicing localization using residual image and residual-based fully convolutional network

Chen, Beijing; Qi, Xiaoming; Zhou, Yang; Yang, Guanyu; Zheng, Yuhui; Xiao, Bin

doi:10.1016/j.jvcir.2020.102967

Cited by 13 publications

(16 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the level of localization, these methods can be divided into two categories: block-level [13][14][15][16] and pixel-level [17][18][19][20][21][22] . In block-level methods [13][14][15][16] , the spliced image is first divided into blocks and then the divided blocks are input into the deep neural network to classify into two categories: spliced ones and real ones.…”

Section: The Deep Learning-based Methods Utilize Network Training To Obtain Expected Features Automaticallymentioning

confidence: 99%

“…To evaluate the performance of the proposed method comprehensively, we compare the F-measure metric in terms of accuracy, generalization and robustness abilities, respectively. [17] 0.5001 0.5700 0.5232 MFCN [18] 0.6351 0.6044 0.6275 QFCN + CRF [19] 0.6626 0.7218 0.6879 FCN + RPN + CRF [20] 0.6837 0.7825 0.7388 Noiseprint [21] 0.7019 0.7924 0.7401 ResFCN [22] 0.7021 0.8087 0.7580 RGB-N [23] 0.6279 0.5841 0.5904 Ours 0.7486 0.8495 0.7787…”

Section: Experiments On Three Standard Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

A Quaternion Two‐Stream R‐CNN Network for Pixel‐Level Color Image Splicing Localization

Chen

Gao

et al. 2021

Chinese J of Electronics

View full text Add to dashboard Cite

Recently, Zhou et al. designed a two‐stream faster Region‐Convolutional neural networks (R‐CNN) model RGB‐N for color image splicing localization in CVPR2018. However, the RGB‐N locates spliced regions only at block‐level and ignores the entirety and inherent correlation of three channels. Therefore, an improved quaternion two‐stream R‐CNN model is proposed to solve these drawbacks: a mask branch combining fully convolutional network and condition random field is added for locating spliced regions at pixel‐level; quaternion representation of color images is used to process color spliced images in a holistical way. In addition, feature pyramid network based on quaternion residual network is considered to extract multi‐scale features for color spliced images; attention region proposal network is combined with attention mechanism and is designed to pay more attention to the spliced regions; a high‐pass filter designed for image splicing detection specifically is adopted to replace steganalysis rich model filter in the RGB‐N to obtain noise input for the noise stream. Experimental results on a new synthetic dataset and three standard forgery datasets demonstrate that the proposed method is superior to the existing methods in the abilities of localization, generalization, and robustness.

show abstract

Section: The Deep Learning-based Methods Utilize Network Training To Obtain Expected Features Automaticallymentioning

confidence: 99%

Section: Experiments On Three Standard Datasetsmentioning

confidence: 99%

A Quaternion Two‐Stream R‐CNN Network for Pixel‐Level Color Image Splicing Localization

Chen

Gao

et al. 2021

Chinese J of Electronics

View full text Add to dashboard Cite

show abstract

“…Residual-based [34] descriptors have proven extremely effective for a number of image forensic applications. Experimental results based on residual-based fully convolutional network [35] for image tampering detection for various datasets performed better than some existing methods in generalization ability, localization ability, and robustness against additional operations.…”

Section: Related Workmentioning

confidence: 93%

Cloud-Based Fusion of Residual Exploitation-Based Convolutional Neural Network Models for Image Tampering Detection in Bioinformatics

Doegar

Hiriyannaiah

Matt³

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

Cloud computing has evolved in various application areas such as medical imaging and bioinformatics. It raises the issues of privacy and tampering in the images especially related to the medical field and bioinformatics for various reasons. The digital images are quite vulnerable to be tampered by the interceptors. The credibility of individuals can transform through falsified information in the images. Image tampering detection is an approach to identifying and finding the tampered components in the image. For the efficient detection of image tampering, the sufficient number of features are required which can be achieved by a deep learning architecture-based models without manual feature extraction of functions. In this research work, we have presented and implemented a cloud-based residual exploitation-based deep learning architectures to detect whether or not an image is being tampered. The proposed approach is implemented on the publicly available benchmark MICC-F220 dataset with the k -fold cross-validation approach to avoid the overfitting problem and to evaluate the performance metrics.

show abstract

“…Because deepfake is also a forgery of images, early detection methods can learn from the forgery detection method of images. Recently, a bunch of high-efficient detectors with the new algorithms have been proposed to improve the performance of tampering detection and localization [8,9]. Also, in order to specifically detect deepfake forgery, researchers classify real and fake videos based on intraframe information, interframe information, or special artifact.…”

Section: Forgery Detectionmentioning

confidence: 99%

Countering Spoof: Towards Detecting Deepfake with Multidimensional Biological Signals

Jin

Chen

2021

Security and Communication Networks

View full text Add to dashboard Cite

The deepfake technology is conveniently abused with the low technology threshold, which may bring the huge social security risks. As GAN-based synthesis technology is becoming stronger, various methods are difficult to classify the fake content effectively. However, although the fake content generated by GANs can deceive the human eyes, it ignores the biological signals hidden in the face video. In this paper, we proposed a novel video forensics method with multidimensional biological signals, which extracting the difference of the biological signal between real and fake videos from three dimensions. The experimental results show that our method achieves 98% accuracy on the main public dataset. Compared with other technologies, the proposed method only extracts fake video information and is not limited to a specific generation method, so it is not affected by synthetic methods and has good adaptability.

show abstract

Image splicing localization using residual image and residual-based fully convolutional network

Cited by 13 publications

References 22 publications

A Quaternion Two‐Stream R‐CNN Network for Pixel‐Level Color Image Splicing Localization

A Quaternion Two‐Stream R‐CNN Network for Pixel‐Level Color Image Splicing Localization

Cloud-Based Fusion of Residual Exploitation-Based Convolutional Neural Network Models for Image Tampering Detection in Bioinformatics

Countering Spoof: Towards Detecting Deepfake with Multidimensional Biological Signals

Contact Info

Product

Resources

About