Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (10): 3177-3184.DOI: 10.11772/j.issn.1001-9081.2023101462

• Multimedia computing and computer simulation • Previous Articles     Next Articles

Robust splicing forensic algorithm against high-intensity salt-and-pepper noise

Pengbo WANG1, Wuyang SHAN1(), Jun LI1, Mao TIAN2, Deng ZOU1, Zhanfeng FAN3   

  1. 1.College of Computer Science and Cyber Security,Chengdu University of Technology,Chengdu Sichuan 610059,China
    2.College of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
    3.School of Architecture and Civil Engineering,Chengdu University,Chengdu Sichuan 610106,China
  • Received:2023-11-10 Revised:2024-04-12 Accepted:2024-04-15 Online:2024-10-15 Published:2024-10-10
  • Contact: Wuyang SHAN
  • About author:WANG Pengbo, born in 1998, M. S. candidate. His research interests include image forensics, deep learning.
    LI Jun, born in 1973, Ph. D., professor. His research interests include high performance computing, computer vision, artificial intelligence.
    TIAN Mao, born in 1988, Ph. D., lecturer. His research interests include stereo matching, fusion of point cloud and image, deep learning.
    ZOU Deng, born in 1999, M. S. candidate. His research interests include image forensics, image processing.
    FAN Zhanfeng, born in 1985, Ph. D., lecturer. His research interests include rock dynamics, advanced geological prediction and monitoring measurement for tunnel, numerical calculation of multi-field coupling.
  • Supported by:
    National Natural Science Foundation of China(42001417);Sichuan Provincial Science and Technology Program(2021YFG0298);Open Fund of Sichuan Engineering Research Center for Mechanical Properties and Engineering Technology of Unsaturated Soils(SC-FBHT2022-14)

抗高强度椒盐噪声的鲁棒拼接取证算法

王朋博1, 单武扬1(), 李军1, 田茂2, 邹登1, 范占锋3   

  1. 1.成都理工大学 计算机与网络安全学院,成都 610059
    2.重庆邮电大学 计算机科学与技术学院,重庆 400065
    3.成都大学 建筑与土木工程学院,成都 610106
  • 通讯作者: 单武扬
  • 作者简介:王朋博(1998—),男,河南漯河人,硕士研究生,CCF会员,主要研究方向:图像取证、深度学习
    单武扬(1988—),男,湖南岳阳人,讲师,博士,主要研究方向:多媒体取证、计算机视觉、数据隐藏 shanwuyang@cdut.edu.cn
    李军(1973—),男,湖北潜江人,教授,博士,主要研究方向:高性能计算、计算机视觉、人工智能
    田茂(1988—),男,四川德阳人,讲师,博士,CCF会员,主要研究方向:立体匹配、点云和影像融合、深度学习
    邹登(1999—),男,湖北麻城人,硕士研究生,主要研究方向:图像取证、图像处理
    范占锋(1985—),男,山西运城人,讲师,博士,主要研究方向:岩石动力学、隧道超前地质预报及监控量测、多场耦合数值计算。
  • 基金资助:
    国家自然科学基金资助项目(42001417);四川省科技计划项目(2021YFG0298);四川省非饱和土力学特性及工程技术工程研究中心项目(SC?FBHT2022?14)

Abstract:

In the field of image forensics, image splicing detection technology can identify splicing and locate the splicing area through the analysis of image content. However, in common scenarios like transmission and scanning, salt-and-pepper (s&p) noise appears randomly and inevitably, and as the intensity of the noise increases, the current splicing forensic methods lose effectiveness progressively and might ultimately fail, thereby significantly impacting the effect of existing splicing forensic methods. Therefore, a splicing forensic algorithm against high-intensity s&p noise was proposed. The proposed algorithm was divided into two main parts: preprocessing and splicing forensics. Firstly, in the preprocessing part, a fusion of the ResNet32 and median filter was employed to remove s&p noise from the image, and the damaged image content was restored through the convolutional layer, so as to minimize the influence of s&p noise on splicing forensic part and restore image details. Then, in the splicing forensics part, based on the Siamese network structure, the noise artifacts associated with the image’s uniqueness were extracted, and the spliced area was identified through inconsistency assessment. Experimental results on widely used tampering datasets show that the proposed algorithm achieves good results on both RGB and grayscale images. In a 10% noise scenario, the proposed algorithm increases the Matthews Correlation Coefficient (MCC) value by over 50% compared to FS(Forensic Similarity) and PSCC-Net(Progressive Spatio-Channel Correlation Network) forensic algorithms, validating the effectiveness and advancement of the proposed algorithm in forensic analysis of tampered images with noise.

Key words: image splicing, forgery detection, image denoising, salt-and-pepper (s&p) noise, Convolutional Neural Network (CNN)

摘要:

在图像取证领域,图像拼接检测技术可以通过分析图像内容识别拼接,并定位拼接区域。然而,在传输、扫描等常见场景中,椒盐(s&p)噪声会不可避免地随机出现,且随着噪声强度的增加,当前拼接取证方法的效力将逐渐减弱,甚至失效,极大地影响了现有拼接取证方法的效果。因此,提出一种能够抵御高强度椒盐噪声的拼接取证算法。所提算法分为2个主要部分:预处理部分和拼接取证部分。首先,预处理部分利用ResNet32与中值滤波器的融合,去除图像中的椒盐噪声,并通过卷积层恢复受损的图像内容,从而最大限度地消除椒盐噪声对拼接取证部分的影响并恢复图像细节;其次,拼接取证部分基于暹罗网络结构,提取与图像唯一性相关的噪声伪影,并通过不一致判断识别拼接区域。在通用篡改数据集上的实验结果表明,所提算法在RGB图像和灰度图像上均取得了良好的效果。在10%噪声场景下与FS (Forensic Similarity)和PSCC-Net (Progressive Spatio-Channel Correlation Network)取证算法相比,所提算法将马修斯相关系数(MCC)值提升超过50%,这验证了所提算法在被噪声干扰的篡改图像上取证的有效性和先进性。

关键词: 图像拼接, 伪造检测, 图像去噪, 椒盐噪声, 卷积神经网络

CLC Number: