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...

Full description

Saved in:
Bibliographic Details
Main Authors: Wuyang Shan, Yijie Xie, Pengbo Wang, Deng Zou, Junying Qiu, Jun Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10904222/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850023570290245632
author Wuyang Shan
Yijie Xie
Pengbo Wang
Deng Zou
Junying Qiu
Jun Li
author_facet Wuyang Shan
Yijie Xie
Pengbo Wang
Deng Zou
Junying Qiu
Jun Li
author_sort Wuyang Shan
collection DOAJ
description 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.
format Article
id doaj-art-b2f6432717994ff6827afea642a2ad79
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-b2f6432717994ff6827afea642a2ad792025-08-20T03:01:19ZengIEEEIEEE Access2169-35362025-01-0113383253834110.1109/ACCESS.2025.354583010904222DSNI-Net: Forensic Network for Detecting Splicing in Salt-and-Pepper Noisy ImagesWuyang Shan0https://orcid.org/0000-0002-3689-1728Yijie Xie1https://orcid.org/0009-0002-7373-5772Pengbo Wang2https://orcid.org/0009-0008-7375-8222Deng Zou3https://orcid.org/0009-0006-3639-4146Junying Qiu4https://orcid.org/0009-0005-9909-1620Jun Li5https://orcid.org/0009-0000-8251-191XCollege of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu, ChinaCollege of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu, ChinaCollege of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu, ChinaCollege of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu, ChinaCollege of Fashion and Design Arts, Sichuan Normal University, Chengdu, ChinaCollege of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu, ChinaImage 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.https://ieeexplore.ieee.org/document/10904222/Splicing forensicsimage denoisingsalt-and-pepper noiseconvolutional neural network
spellingShingle Wuyang Shan
Yijie Xie
Pengbo Wang
Deng Zou
Junying Qiu
Jun Li
DSNI-Net: Forensic Network for Detecting Splicing in Salt-and-Pepper Noisy Images
IEEE Access
Splicing forensics
image denoising
salt-and-pepper noise
convolutional neural network
title DSNI-Net: Forensic Network for Detecting Splicing in Salt-and-Pepper Noisy Images
title_full DSNI-Net: Forensic Network for Detecting Splicing in Salt-and-Pepper Noisy Images
title_fullStr DSNI-Net: Forensic Network for Detecting Splicing in Salt-and-Pepper Noisy Images
title_full_unstemmed DSNI-Net: Forensic Network for Detecting Splicing in Salt-and-Pepper Noisy Images
title_short DSNI-Net: Forensic Network for Detecting Splicing in Salt-and-Pepper Noisy Images
title_sort dsni net forensic network for detecting splicing in salt and pepper noisy images
topic Splicing forensics
image denoising
salt-and-pepper noise
convolutional neural network
url https://ieeexplore.ieee.org/document/10904222/
work_keys_str_mv AT wuyangshan dsninetforensicnetworkfordetectingsplicinginsaltandpeppernoisyimages
AT yijiexie dsninetforensicnetworkfordetectingsplicinginsaltandpeppernoisyimages
AT pengbowang dsninetforensicnetworkfordetectingsplicinginsaltandpeppernoisyimages
AT dengzou dsninetforensicnetworkfordetectingsplicinginsaltandpeppernoisyimages
AT junyingqiu dsninetforensicnetworkfordetectingsplicinginsaltandpeppernoisyimages
AT junli dsninetforensicnetworkfordetectingsplicinginsaltandpeppernoisyimages