计算机科学 ›› 2021, Vol. 48 ›› Issue (6A): 43-50.doi: 10.11896/jsjkx.200800020

• 图像处理&多媒体技术 • 上一篇    下一篇

基于离散切比雪夫变换的图像接缝裁剪篡改检测

田洋1, 毕秀丽1, 肖斌1, 李伟生1, 马建峰2   

  1. 1 重庆邮电大学图像认知重点实验室 重庆400065
    2 西安电子科技大学网络与信息安全学院 西安710071
  • 出版日期:2021-06-10 发布日期:2021-06-17
  • 通讯作者: 毕秀丽(bixl@cqupt.edu.cn)
  • 作者简介:tydwyyx163@163.com
  • 基金资助:
    国家自然科学基金(61806032,61976031);国家重点研发计划(2016YFC1000307-3);重庆市教委科学技术研究项目(KJQN201800611);重庆市基础与前沿项目(cstc2018jcyjAX0117);重庆市教委科学技术研究计划重点项目(KJZD-K201800601)

Image Seam Carving Tampering Detection by Discrete Tchebichef Transform

TIAN Yang1, BI Xiu-li1, XIAO Bin1, LI Wei-sheng1, MA Jian-feng2   

  1. 1 Key Laboratory of Image Cognition,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
    2 School of Cyber Engineering,Xidian University,Xi'an 710071,China
  • Online:2021-06-10 Published:2021-06-17
  • About author:TIAN Yang,born in 1995,postgraduate.His main research interests include ima-ge processing and pattern recognition.
    BI Xiu-li,born in 1982,Ph.D,associate professor,is a member of China Computer Federation.Her main research interests include digital image processing and multimedia information security.
  • Supported by:
    National Natural Science Foundation of China(61806032,61976031),National Science & Technology Major Project(2016YFC1000307-3),Scientific & Technological Research Program of Chongqing Municipal Education Commission(KJQN201800611),Chongqing Research Program of Application Foundation & Advanced Technology(cstc2018jcyjAX0117) and Scientific & Technological Key Research Program of Chongqing Municipal Education Commission(KJZD-K201800601).

摘要: 接缝裁剪(Seam Carving)作为近些年来热门的图像缩放技术之一,常被用于图像恶意篡改。当前对Seam Carving篡改的检测方法并不多,并均是针对JPEG格式图像,且在篡改比例较小时,检测准确率不高。文中方法利用离散切比雪夫变换后系数矩阵中的分布特点来提取特征以达到对图像接缝裁剪篡改的检测,并且该方法适用于多种图像格式,在小比例篡改的情况下依然保持较高的分类准确。利用离散切比雪夫变换(Discrete Tchebichef Transform,DTT)得到变换后的系数矩阵,提取Seam Carving篡改的痕迹,实现了对Seam Carving的篡改检测。所提方法首先将待检测图像分成8×8不重叠块,对每一个8×8块进行DTT变换,得到变换后的DTT系数矩阵;然后在每一块中分别计算DTT系数间的差异,再通过系数差异直方图得到统计矩阵,从统计矩阵中提取特征;最后使用支持向量机(Support Vector Machine,SVM)进行训练得到预测模型,实现对图像Seam Carving篡改的检测。实验结果表明,所提方法不仅适用于JPEG格式和TIFF格式的篡改图像,对小比例篡改也能达到较高的检测准确率。

关键词: 接缝裁剪, 篡改检测, 离散切比雪夫变换, 图像取证, 图像缩放

Abstract: As one of the most popular image scaling technologies in recent years,seam carving is often used for malicious tampering.We find that there are two shortcomings in the current research work of seam carving tamper detection.First,the detection methods are basically aimed at tampered JPEG image.For tampered TIFF image,the current detection methods have low accuracy.Second,when the ratio of seam carving tampering is small,the classification accuracy is relatively low.In order to solve these problems,this paper proposes a seam car-ving tamper detection method based on discrete Tchebichef transform.The tamper detection method is no longer limited to the image format,can effectively detect the tampered images of various formats,and maintain a high classification accuracy.In addition,when the tampering ratio is small,this method will not fail,and has a high classification accuracy.The method in this paper users the distribution characteristics of the coefficients in the coefficient matrix after the discrete Tchebichef transform to extract features to detect seam carved images.Moreover,this method is suitable for all kinds of image formats,and maintains a high classification accuracy under the condition of small tampering ratio.The proposed method makes use of the distribution characteristics of the coefficients in the coefficient matrix after discrete Tchebichef transform.After image segmentation and discrete Tchebichef transform,the value of the coefficient in the upper left corner of each block is very large,and the value in other positions is very small.The trace of seam carving is extracted and the tamper detection of seam carving is realized.Based on the characteristics of coefficient distribution in discrete Tchebichef transform coefficient matrix,the classification accuracy will not be affected by compression quality factor and will not change with the change of compression quality factor.The steps of this detection method are as follows.Firstly,the images are divided into 8×8 non-overlapping blocks,and then each block of the image is transformed by discrete Tchebichef transform to get the transformed coefficient matrix.Due to the characteristics of discrete Tchebichef transform,the coefficients of the upper left corner of each 8×8 block of the coefficient matrix are very large,and the coefficients of other positions are very small,so the differences between coefficients are calculated in each block of the coefficient matrix,and the histogram of the differences between coefficients is obtained.Finally,the statistical matrix is obtained from the histogram of the differences between the coefficients,and the features are extracted from the statistical matrix.The extracted features are sent to SVM for training,and a classification model is obtained.In this paper,a seam car-ving tamper detection method based on discrete Tchebichef transform is proposed to classify original images and tampered images.The experimental results show that this method can achieve high classification accuracy.The detection method based on discrete Tchebichef transform proposed in this paper can achieve high classification accuracy both in JPEG tampered image and TIFF tampered image,and also can achieve high detection accuracy for small-scale tampering.

Key words: Seam carving, Tamper detection, Discrete Tchebichef transform, Image forensics, Image resizing

中图分类号: 

  • TP301
[1] AVIDAN S,SHAMIR A.Seam carving for content-aware image resizing [C]//ACM SIGGRAPH.2007:10-es.
[2] WATTANACHOTE K,SHIH T K,CHANG W L,et al.Tamper detection of JPEG image due to seam modifications [J].IEEE Transactions on Information Forensics,2015(10):2477-2491.
[3] SARKAR A,NATARAJ L,MANJUNATH B S.Detection ofseam carving and localization of seam insertions in digital images[C]//Proceedings of the Proceedings of the 11th ACM Workshop on Multimedia and Security.2009.
[4] GUO J C,WANG Q Z,ZHAO J,et al.A Method of Seam Carving Forensics Based on LBP and Markov Features [J].Journal of University ofElectronic Science,2018,47:481-485.
[5] ZHANG D,YANG G,LI F,et al.Detecting seam carved images using uniform local binary patterns [J].Multimedia Tools and Applications,2020,79(13):8415-8430.
[6] WEI J D,LIN Y J,WU Y J.A patch analysis method to detect seam carved images [J].Pattern Recognition Letters,2014,36:100-106.
[7] SCHAEFER G,STICH M.UCID:An uncompressed color image database[C]//Proceedings of the Storage and RetrievalMe-thods and Applications for Multimedia 2004.International Society for Optics and Photonics,2003.
[8] RYU S J,LEE H Y,LEE H K,et al.Detecting trace of seam carving for forensic analysis [J].Ice Transactions on Information and Systems,2014,97:1304-1311.
[9] YIN T,YANG G,LI L,et al.Detecting seam carving basedimage resizing using local binary patterns [J].Computer and Security.2015,55:130-141.
[10] LU W,WU M.Seam carving estimation using forensic hash[C]//Proceedings of the Proceedings of the thirteenth ACM multimedia workshop on Multimedia and Security.2011.
[11] LIU Q.An approach to detecting JPEG down-recompression and seam carving forgery under recompression anti-forensics [J].Pattern Recognition,2017,6:35-46.
[12] LIU Q.Exposing seam carving forgery under recompression attacks by hybrid large feature mining[C]//Proceedings of the 2016 23rd International Conference on Pattern Recognition (ICPR).2016.
[13] LIU Q,CHEN Z J.Improved approaches with calibrated neighboring joint density to steganalysis and seam-carved forgery detectionin JPEG images [C]//ACM Transactions on Intelligent Systems and Technology (TIST).2014:1-30.
[14] LU M,NIU S Z.Detection of Image Seam Carving Using a Novel Pattern[J].Computational Intelligence and Neuroscience,2019,2019:9492358.
[15] MUKUNDAN R,ONG S,LEE P A.Image analysis by Tche-bichef moments [J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2001,10:1357-1364.
[16] NAM S H,AHN W,YU J,et al.Deep Convolutional Neural Network for Identifying Seam-Carving Forgery [J].IEEE Transactions on Circuits and Systems for Video Technology,2020(99):1-1.
[17] WEI J D,CHENG H J,CHANG C W.Hopfield network-based approach to detect seam-carved images and identify tampered regions [J].Neural Computing and Applications,2019,31(10):6479-6492.
[18] YE J,SHI Y,XU G,et al.A Convolutional Neural NetworkBased Seam Carving Detection Scheme for Uncompressed Digital Images[C]//Proceedings of the International Workshop on Digi-tal Watermarking.2018.
[1] 张开强, 蒋从锋, 程小兰, 贾刚勇, 张纪林, 万健. 多分辨率下资源感知的图像目标自适应缩放检测[J]. 计算机科学, 2021, 48(4): 180-186.
[2] 尚进跃, 毕秀丽, 肖斌, 李伟生. 基于DCT系数哈希的图像篡改检测算法[J]. 计算机科学, 2020, 47(6): 310-315.
[3] 郑秋梅, 刘楠, 王风华. 基于复杂攻击的脆弱水印图像完整性认证算法[J]. 计算机科学, 2020, 47(10): 332-338.
[4] 邢文博, 杜志淳. JPEG图像文件头取证[J]. 计算机科学, 2019, 46(6A): 353-357.
[5] 邢文博, 杜志淳. 数字图像复制粘贴篡改取证[J]. 计算机科学, 2019, 46(6A): 380-384.
[6] 王志锋, 朱琳, 曾春艳, 闵秋莎, 夏丹. 数字图像重压缩检测研究综述[J]. 计算机科学, 2018, 45(9): 20-29.
[7] 罗霄阳,霍宏涛,王梦思,陈亚飞. 基于多残差马尔科夫模型的图像拼接检测[J]. 计算机科学, 2018, 45(4): 173-177.
[8] 周燕,曾凡智,赵慧民. 基于压缩感知的视频双水印算法研究[J]. 计算机科学, 2016, 43(5): 132-139.
[9] 隋莉莉,汪传建. 基于弱水印的地理数据拓扑完整性检验方法[J]. 计算机科学, 2016, 43(2): 183-187.
[10] 林晓,张晓煜,马利庄. 基于缝裁剪和变形的图像缩放方法[J]. 计算机科学, 2015, 42(9): 289-292.
[11] 刘丽娟,林小竹. 基于背景噪声的图像盲篡改检测[J]. 计算机科学, 2014, 41(Z11): 136-138.
[12] 林晓,沈洋,马利庄,邹盼盼. 显著物体形状结构保持的图像缩放方法[J]. 计算机科学, 2014, 41(12): 288-292.
[13] 康晓兵,魏生民. 一种基于自适应闭值的图像伪造检测算法[J]. 计算机科学, 2011, 38(3): 295-299.
[14] 肖磊. 一种具有高攻击类型判别能力的图像空域半脆弱水印算法[J]. 计算机科学, 2010, 37(2): 286-289.
[15] 王鑫,鲁志波. 基于JPEG块效应差异的图像篡改区域自动定位[J]. 计算机科学, 2010, 37(2): 269-273.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 方磊, 武泽慧, 魏强. 二进制代码相似性检测技术综述[J]. 计算机科学, 2021, 48(5): 1 -8 .
[2] 朱雨, 庞建民, 徐金龙, 陶小涵, 王军. 面向SW26010处理器的三维Stencil自适应分块参数算法[J]. 计算机科学, 2021, 48(6): 10 -18 .
[3] . 目录[J]. 计算机科学, 2021, 48(6A): 0 .
[4] 冯芙蓉, 张兆功. 目标轮廓检测技术新进展[J]. 计算机科学, 2021, 48(6A): 1 -9 .
[5] 孙正, 张小雪. 生物光声成像中声反射伪影抑制方法的研究进展[J]. 计算机科学, 2021, 48(6A): 10 -14 .
[6] 周欣, 刘硕迪, 潘薇, 陈媛媛. 自然交通场景中的车辆颜色识别[J]. 计算机科学, 2021, 48(6A): 15 -20 .
[7] 黄雪冰, 魏佳艺, 沈文宇, 凌力. 基于自适应加权重复值滤波和同态滤波的MR图像增强[J]. 计算机科学, 2021, 48(6A): 21 -27 .
[8] 江妍, 马瑜, 梁远哲, 王原, 李光昊, 马鼎. 基于分数阶麻雀搜索优化OTSU肺组织分割算法[J]. 计算机科学, 2021, 48(6A): 28 -32 .
[9] 张子丞, 谭志苇, 张晨瑞, 王旋, 刘晓璇, 俞一彪. 基于高低频带对数能量谱比贝叶斯决策的语音端点检测[J]. 计算机科学, 2021, 48(6A): 33 -37 .
[10] 崔雯昊, 蒋慕蓉, 杨磊, 傅鹏铭, 朱凌霄. 结合MCycleGAN与RFCNN实现太阳斑点图高分辨重建[J]. 计算机科学, 2021, 48(6A): 38 -42 .