Wuyang Shan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Wuyang Shan has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Aoling Liu
College of Computer Science and Cyber Security(Pilot Software College), Chengdu University of Technology, Chengdu, China
2 shared publications - Deng Zou
College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu, China
2 shared publications Hang Su
2 shared publicationsJiarui Cao
2 shared publicationsJingwei Si
2 shared publications- Jun Li
College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu 610059, China
2 shared publications
Latest Publications
- 1 November 2026
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 122
RCSCAC-Net: a robust image tampering localization network for Gaussian-blurred forgery images
- 1 November 2026
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 122
RCSCAC-Net: a robust image tampering localization network for Gaussian-blurred forgery images
- Open Access
- 2 July 2026
- Published by Elsevier in SSRN Electronic Journal
RCSCAC-Net: A Robust Image Tampering Localization Network for Gaussian-Blurred Forgery Images
Image tampering localization has advanced significantly with deep learning, but existing methods often degrade under Gaussian blur, which suppresses high-frequency components and weakens subtle forgery traces such as edge and texture inconsistencies. To improve robustness against blur degradation, we propose RCSCAC-Net, a two-stage tampering localization network consisting of a restore module and a localization module. The restore module first recovers blur-degraded tampering clues, providing enhanced forensic features for the localization module to identify manipulated regions. The two modules are jointly trained, enabling the restore module to focus on forgery-relevant detail restoration while helping the localization module capture subtle tampering traces more effectively. Experiments on multiple public datasets demonstrate that RCSCAC-Net achieves competitive performance against recent state-of-the-art methods and maintains stable localization accuracy across various Gaussian blur intensities.
- 2 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRCSCAC-Net: A Robust Image Tampering Localization Network for Gaussian-Blurred Forgery Images
Image tampering localization has advanced significantly with deep learning, but existing methods often degrade under Gaussian blur, which suppresses high-frequency components and weakens subtle forgery traces such as edge and texture inconsistencies. To improve robustness against blur degradation, we propose RCSCAC-Net, a two-stage tampering localization network consisting of a restore module and a localization module. The restore module first recovers blur-degraded tampering clues, providing enhanced forensic features for the localization module to identify manipulated regions. The two modules are jointly trained, enabling the restore module to focus on forgery-relevant detail restoration while helping the localization module capture subtle tampering traces more effectively. Experiments on multiple public datasets demonstrate that RCSCAC-Net achieves competitive performance against recent state-of-the-art methods and maintains stable localization accuracy across various Gaussian blur intensities.
- 5 March 2026
- Published by Elsevier in Neural Networks
- Vol. 200, 108813
RIFoL: A robust image forgery localization network for noisy images
- 5 March 2026
- Published by Elsevier in Neural Networks
- Vol. 200, 108813
RIFoL: A robust image forgery localization network for noisy images
- Open Access
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 38325-38341
DSNI-Net: Forensic Network for Detecting Splicing in Salt-and-Pepper Noisy Images
Image splicing forensics technology is an important way to detect and locate spliced areas in naturally tampered images. However, common noise, especially salt-and-pepper(s&p) noise, can change pixel values to 0 or 255, significantly reducing the accuracy of splicing forensic methods. As the noise intensity increases, the impact on forensic methods gradually increases. This paper proposes a forensic method to enhance the robustness of the forensic method in scenarios with high-intensity s&p noise called forensic network for detecting splicing in s&p noisy images (DSNI-Net). The image is first denoised using a combination of residual network and median layer (ML) before forensics. The CNN network extracts shallow and deep feature channels in the image, uses ML to remove s&p noise, and reconstructs the image content through the convolution structure to restore image details. Secondly, the feature comparison structure is used to extract tampering traces during the forensic process. This ensures that the final extracted features are uniquely related to the image itself and are used to reveal areas of image tampering. Experimental results on noisy datasets demonstrate the robustness and effectiveness of DSNI-Net under various intensities of s&p noise. Notably, at a noise intensity level of 5%, DSNI-Net improves forensic performance by 37%. Generalization experiments further confirm that DSNI-Net is robust against other types of noise and JPEG compression.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 38325-38341
Open AccessDSNI-Net: Forensic Network for Detecting Splicing in Salt-and-Pepper Noisy Images
Image splicing forensics technology is an important way to detect and locate spliced areas in naturally tampered images. However, common noise, especially salt-and-pepper(s&p) noise, can change pixel values to 0 or 255, significantly reducing the accuracy of splicing forensic methods. As the noise intensity increases, the impact on forensic methods gradually increases. This paper proposes a forensic method to enhance the robustness of the forensic method in scenarios with high-intensity s&p noise called forensic network for detecting splicing in s&p noisy images (DSNI-Net). The image is first denoised using a combination of residual network and median layer (ML) before forensics. The CNN network extracts shallow and deep feature channels in the image, uses ML to remove s&p noise, and reconstructs the image content through the convolution structure to restore image details. Secondly, the feature comparison structure is used to extract tampering traces during the forensic process. This ensures that the final extracted features are uniquely related to the image itself and are used to reveal areas of image tampering. Experimental results on noisy datasets demonstrate the robustness and effectiveness of DSNI-Net under various intensities of s&p noise. Notably, at a noise intensity level of 5%, DSNI-Net improves forensic performance by 37%. Generalization experiments further confirm that DSNI-Net is robust against other types of noise and JPEG compression.
- 13 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 2095-2099
SLRID: A Robust Image Tampering Localization Framework for Extremely Scaled Forgery Images
Existing tampering localization methods perform poorly when localizing scaled images that are missing high-frequency forensic traces. Preserving these traces is critical for accurately localizing tampering because scaling operations can obscure crucial details and introduce artifacts and distortions. To address this issue, we propose a simple yet effective tampering localization framework for scaled images, named SLRID. The framework consists of two components: the Symlet Wavelet Recovery Module (SLR) and the Detector Module (SE-RRU-net). The SLR employs an invertible network of the Symlet Wavelet Transform to simulate the loss of information in a scaled image caused by tampering, achieving high-fidelity restoration of high-frequency forensic traces. The SE-RRU-net network utilizes an end-to-end image segmentation network (RRU-net) for tampering localization, incorporating a Spatial Channel Squeezing and Excitation (SCSE) mechanism to enhance the extraction of forgery-related features in scaled images. Results indicate that the SLRID framework outperforms existing state-of-the-art methods in detecting forged images during scaling operations.
- 13 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 2095-2099
SLRID: A Robust Image Tampering Localization Framework for Extremely Scaled Forgery Images
Existing tampering localization methods perform poorly when localizing scaled images that are missing high-frequency forensic traces. Preserving these traces is critical for accurately localizing tampering because scaling operations can obscure crucial details and introduce artifacts and distortions. To address this issue, we propose a simple yet effective tampering localization framework for scaled images, named SLRID. The framework consists of two components: the Symlet Wavelet Recovery Module (SLR) and the Detector Module (SE-RRU-net). The SLR employs an invertible network of the Symlet Wavelet Transform to simulate the loss of information in a scaled image caused by tampering, achieving high-fidelity restoration of high-frequency forensic traces. The SE-RRU-net network utilizes an end-to-end image segmentation network (RRU-net) for tampering localization, incorporating a Spatial Channel Squeezing and Excitation (SCSE) mechanism to enhance the extraction of forgery-related features in scaled images. Results indicate that the SLRID framework outperforms existing state-of-the-art methods in detecting forged images during scaling operations.
- Open Access
- 30 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 20326-20340
RIFD-Net: A Robust Image Forgery Detection Network
Image splicing forensic technologies reveal manipulations that add or remove objects from images. However, the performance of existing splicing forensic methods is fatally degraded when detecting noisy images, as they often ignore the influence of image noise. In this paper, we propose a new forgery detection network called the robust image forgery detection network (RIFD-Net) based on convolutional neural networks (CNNs). With the help of multi-classifiers and a denoising network, RIFD-Net can effectively filter out multiple types of image noise before forgery detection. To determine the extent of tampering, we follow the Siamese network to calculate the similarity between two image patches, without prior knowledge of forensic traces. Results from extensive experiments on benchmark datasets indicate that our method outperforms existing image splicing forensic methods, achieving a substantial improvement of over 20% in the mean average precision (mAP) for forgery detection. Furthermore, RIFD-Net accurately locates splice areas, even in the presence of noise.
- 30 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 20326-20340
Open AccessRIFD-Net: A Robust Image Forgery Detection Network
Image splicing forensic technologies reveal manipulations that add or remove objects from images. However, the performance of existing splicing forensic methods is fatally degraded when detecting noisy images, as they often ignore the influence of image noise. In this paper, we propose a new forgery detection network called the robust image forgery detection network (RIFD-Net) based on convolutional neural networks (CNNs). With the help of multi-classifiers and a denoising network, RIFD-Net can effectively filter out multiple types of image noise before forgery detection. To determine the extent of tampering, we follow the Siamese network to calculate the similarity between two image patches, without prior knowledge of forensic traces. Results from extensive experiments on benchmark datasets indicate that our method outperforms existing image splicing forensic methods, achieving a substantial improvement of over 20% in the mean average precision (mAP) for forgery detection. Furthermore, RIFD-Net accurately locates splice areas, even in the presence of noise.
- 1 February 2019
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 71, 138-146
Robust contrast enhancement forensics based on convolutional neural networks
- 1 February 2019
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 71, 138-146
Robust contrast enhancement forensics based on convolutional neural networks
- Open Access
- 24 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 17174-17183
Robust Median Filtering Forensics Using Image Deblocking and Filtered Residual Fusion
Median filtering (MF) is frequently applied to conceal traces of forgery and therefore can provide indirect forensic evidence of tampering when investigating composite images. Existing MF forensic methods however, ignore how JPEG compression affects median filtered images, resulting in heavy performance degradation when detecting filtered images stored in the JPEG format. In this paper, we propose a new robust MF forensic method based on a modified convolutional neural network (CNN). Firstly, relying on the analysis of the influence on median filtered images caused by JPEG compression, we effectively suppress the interference using image deblocking. Secondly, the fingerprints left by MF are highlighted via filtered residual fusion. These two functions are fulfilled with a deblocking layer and a fused filtered residual (FFR) layer. Finally, the output of the FFR layer becomes input when extracting multiple features for further classification using a tailor-made CNN. Extensive experimental results show that the proposed method outperforms the state-of-the-art methods in both JPEG compressed and small size MF image detection.
- 24 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 17174-17183
Open AccessRobust Median Filtering Forensics Using Image Deblocking and Filtered Residual Fusion
Median filtering (MF) is frequently applied to conceal traces of forgery and therefore can provide indirect forensic evidence of tampering when investigating composite images. Existing MF forensic methods however, ignore how JPEG compression affects median filtered images, resulting in heavy performance degradation when detecting filtered images stored in the JPEG format. In this paper, we propose a new robust MF forensic method based on a modified convolutional neural network (CNN). Firstly, relying on the analysis of the influence on median filtered images caused by JPEG compression, we effectively suppress the interference using image deblocking. Secondly, the fingerprints left by MF are highlighted via filtered residual fusion. These two functions are fulfilled with a deblocking layer and a fused filtered residual (FFR) layer. Finally, the output of the FFR layer becomes input when extracting multiple features for further classification using a tailor-made CNN. Extensive experimental results show that the proposed method outperforms the state-of-the-art methods in both JPEG compressed and small size MF image detection.
- 1 July 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 790-793
Analysis and comparison of holographic and traditional digital image watermarking in DWT domain
This paper compares holographic and traditional digital image watermarking by a watermarking algorithm in DWT domain, in which the four sub images of 1-scale wavelet transformed watermark image are embedded into the four corresponding images of 2-scales wavelet transformed host image respectively. By this watermarking algorithm, test results show that the hidden images of holographic watermarking survive geometric distortion more than the traditional one, especially cropping, and the Gaussian filter, Gaussian noise and JPEG compress resilient properties of traditional watermarking are a little better than the holographic watermarking.
- 1 July 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 790-793
Analysis and comparison of holographic and traditional digital image watermarking in DWT domain
This paper compares holographic and traditional digital image watermarking by a watermarking algorithm in DWT domain, in which the four sub images of 1-scale wavelet transformed watermark image are embedded into the four corresponding images of 2-scales wavelet transformed host image respectively. By this watermarking algorithm, test results show that the hidden images of holographic watermarking survive geometric distortion more than the traditional one, especially cropping, and the Gaussian filter, Gaussian noise and JPEG compress resilient properties of traditional watermarking are a little better than the holographic watermarking.