计算机科学 ›› 2017, Vol. 44 ›› Issue (6): 150-154.doi: 10.11896/j.issn.1002-137X.2017.06.025

• 信息安全 • 上一篇    下一篇

结合游程长度与共生矩阵的图像拼接篡改检测方法

苏慧嘉,郑继明   

  1. 重庆邮电大学计算机科学与技术学院 重庆400065,重庆邮电大学理学院 重庆400065
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受重庆市教委科学技术研究项目(KJ1400428)资助

Image Splicing Blind Detection Method Combined RLRN with GLCM

SU Hui-jia and ZHENG Ji-ming   

  • Online:2018-11-13 Published:2018-11-13

摘要: 针对拼接图像篡改鉴别问题,研究了运用游程长度和灰度共生矩阵等统计特征进行图像盲检测的算法。该算法将拼接篡改检测问题转换为二分类模式识别问题,在图像的色度通道Cb和Cr中提取游程长度特征,并将其与灰度共生矩阵特征相结合,然后以结合后的新的特征向量训练LibSVM作为最后的分类器,确定所给图像是否被拼接篡改。实验结果显示,在彩色图像测试库CASIA v2.0上,利用融合后的特征检测图像使识别率得到较大提高,同时该算法在复制粘贴篡改方面也有较好的识别性能。

关键词: 图像拼接篡改,游程长度特征,灰度共生矩阵,支持向量机

Abstract: An algorithm on blind detection of splicing images by using the statistical characteristics with run-length and gray-level co-occurrence matrix(GLCM) features was researched.Splicing detection can be treated as a two-class pattern problem.This paper proposed an enhanced technique for blind detection of image splicing.It extracts the run-length run-number(RLRN) in CbCr chroma space and combines with GLCM feature to detect the artifacts introduced by the tampering operation.Then,the LibSVM is exploited to classify the authentic and spliced images.The experiment results demonstrate that the proposed algorithm not only improves the accurate recognition rate in CASIA v2.0 dataset,but also can achieve well copy-move tampered detection.

Key words: Image splicing detection,Run-length run-number(RLRN),Gray-level co-occurrence matrix(GLCM),Support vector machine(SVM)

[1] NG T T,CHANG S F.A Model for Image Splicing[C]∥International Conference on Image Processing.2004:1169-1172.
[2] SHI Y Q,CHEN C,CHEN W.A Natural Image Model Approa-ch to Splicing Detection[C]∥Proceedings of the 9th Workshop on Multimedia & Security.2007:51-62.
[3] DVMM Laboratory of Columbia University:Columbia Image Sp-licing Detection Evaluation Dataset.http://www.ee.columbia.edu/ln/dvmm/downloads/AuthSplicedDataSet/photographers.html.
[4] HE Z,SUN W,LU W.Digital image splicing detection based on approximate run length[J].Pattern Recognition Letters,2011,2(12):1591-1597.
[5] SHI Z N,SHEN X J,CHEN H P,et al.Blind Detection of Image Splicing Based on Fuzzy Run-Length[C]∥International Conference on Computer and Information Technology.2015:915-920.
[6] LI S H,CHEN G C,SU B,et al.Blind Detection of Splicing Ima-ge Based on Gray Level Co-occurrence Matrix of Image DCT Domain[J].Journal of Shanghai Jiaotong University,2011,5(10):1547-1551.(in Chinese) 李生红,陈古春,苏波,等.基于图片DCT域共生矩阵的图像拼接盲检测[J].上海交通大学学报,2011,5(10):1547-1551.
[7] LI Y,ZHONG L,LI J.Detection of Image Splicing ForgeryBased on LBP and Co-occurrence Matrix[J].Journal of Wuhan University,2015,1(6):517-524.(in Chinese) 李燕,钟磊,李健.基于LBP和共生矩阵的图像拼接篡改检测[J].武汉大学学报,2015,1(6):517-524.
[8] DONG J,WANG W,TAN T,et al.Run-length and edge statistics based approach for image splicing detection [C]∥Digital Watermarking.2008:76-87.
[9] MOGHADDASI Z,JALAB H A,NOOR,et al.Improving RLRN Image Splicing Detection with the Use of PCA and Kernel PCA [J].The Scientific World Journal,2013,4:606570.
[10] MUHAMMAD G,AL M H,HUSSAIN M,et al.Copy Move Image Forgery Detection Method Using Steerable Pyramid Transform and Texture Descriptor [C]∥Image Processing and Analysis.2013:1586-1592.
[11] EL-ALFY E S M,QURESHI M A.Combining spatial and DCT based Markov features for enhanced blind detection of image splicing[J].Pattern Analysis and Applications,2015,18(3):713-723.
[12] SHI Y Q,CHEN C,XUAN G.Steganalysis Versus Splicing Detection [C]∥International Workshop on Digital Watermarking.2007:158-172.
[13] AMANI A,MUHAMMAD H,HATIM A.Splicing Image Forgery Detection Based on DCT and Local Binary Pattern [C]∥GlobalSIP.2013:253-256.
[14] GALLOWAY M M.Texture analysis using gray level run le-ngths[J].Graphics Image Process,1975,4(2):172-179.
[15] HARALICK R M,SHANMUGAM K,DINSTEIN I.TexturalFeatures for Image Classification[J].IEEE Transactions on System,Man and Cybernetics,1973,SMC-3(6):610-621.
[16] YAO H Y,LI B C.Generalized Co-occurrence Matrix Method for Content-based Image Retrieval[J].Computer Engineering and Applications,2004,0(34):98-103.(in Chinese) 姚宏宇,李弼程.基于广义图像灰度共生矩阵的图像检索方法[J].计算机工程与应用,2004,0(34):98-103.
[17] CHANG C C,LIN C J.LIBSVM:A Library for Support Vector Machines.http://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html#nuandone.
[18] National Lab of Pattern Recognition,Institute of Automation,Chinese Academy of Science.CASIA Tampered Image Detection Evaluation Database(CASIA TIDE v2.0).http://forensics.idealtest.org:8080/index_v2.html.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!