抗高强度椒盐噪声的鲁棒拼接取证算法  

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

作　　者：王朋博 单武扬 李军[1] 田茂 邹登 范占锋 WANG Pengbo;SHAN Wuyang;LI Jun;TIAN Mao;ZOU Deng;FAN Zhanfeng(College of Computer Science and Cyber Security,Chengdu University of Technology,Chengdu Sichuan 610059,China;College of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;School of Architecture and Civil Engineering,Chengdu University,Chengdu Sichuan 610106,China)

机构地区：[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

出　　处：《计算机应用》2024年第10期3177-3184,共8页journal of Computer Applications

基　　金：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)。

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。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-andpepper(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.

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 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]