抗真实相似物体干扰的图像区域复制篡改检测算法研究

计算机科学 ›› 2015, Vol. 42 ›› Issue (Z6): 226-230.

抗真实相似物体干扰的图像区域复制篡改检测算法研究

崔文成,梁爽爽,邵虹,王海宇

沈阳工业大学信息科学与工程学院沈阳110870,沈阳工业大学信息科学与工程学院沈阳110870,沈阳工业大学信息科学与工程学院沈阳110870,沈阳工业大学信息科学与工程学院沈阳110870

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受辽宁省自然科学基金(201202162),辽宁省高等学校优秀人才支持计划(LJQ2013013)资助

Research on Detection of Image Region-duplication Forgery Affected by Intrinsically Identical Objects

CUI Wen-cheng, LIANG Shuang-shuang, SHAO Hong and WANG Hai-yu

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 对图像进行区域复制篡改检测时,真实相似物体会使检测结果出现假阳性。针对该问题,提出一种基于密度的局部离群点与簇内特征点紧凑度相结合的检测算法。首先对图像进行复制篡改检测,将检测到的复制区域和篡改区域作为可疑区域对进行二次判断。然后对可疑区域对进行SIFT特征点提取,并采用双向匹配提高准确率。再通过仿高斯影响函数估算匹配点在其邻域内的影响因子,利用影响因子对局部可达密度加权进行局部离群因子计算,继而与近邻传播聚类后计算的平均簇内紧凑度相结合,实现匹配点的分布估计,最后通过支持向量机进行可疑区域的最终判别。实验结果表明,上述方法可以有效抵抗真实相似物体干扰,具有高准确率与低误判率。

Abstract: Intrinsically identical objects can cause false positive when the image is detected by region-duplication forgerydetection.A detection algorithm was proposed based on local outlier estimation and cluster compactness.Firstly,SIFT feature is extracted and bidirectional matching is applied.Then local outlier factor and local reachability density are applied to analyze distribution of matching points after estimating influence on its neighborhood by counterfeit-Gaussian influence function,and combined with cluster compactness after affinity propagation Clustering.Finally,the support vector machine is applied to distinguish the intrinsically identical objects.Experimental results show that the proposed method,which has high accuracy rate and low false detection rate,can resist intrinsically identical objects interference effectively.

Key words: Tamper detection,Region-duplication,Intrinsically identical objects,Local outlier factor,Cluster compactness

崔文成,梁爽爽,邵虹,王海宇. 抗真实相似物体干扰的图像区域复制篡改检测算法研究[J]. 计算机科学, 2015, 42(Z6): 226-230. https://doi.org/

CUI Wen-cheng, LIANG Shuang-shuang, SHAO Hong and WANG Hai-yu. Research on Detection of Image Region-duplication Forgery Affected by Intrinsically Identical Objects[J]. Computer Science, 2015, 42(Z6): 226-230. https://doi.org/

参考文献

[1] Farid H.Creating and detecting doctored and virtual images:implications to the child photography prevention act[R].Technical Report,TR2004-518,Dartmouth College,Computer Science,2004
[2] 骆伟祺,黄继武,丘国平.鲁棒的区域复制图像篡改检测技术[J].计算机学报,2007,30(11):1998-2007
[3] 秦娟,李峰,向凌云.采用圆谐-傅里叶矩的图像区域复制粘贴篡改检测[J].中国图像图形学报,2013,18(8):919-923
[4] 赵洁,郭继昌,武斌,等.基于几何均值分解的图像区域复制篡改检测方法[J].小型微型计算机系统,2012,33(9):2105-2108
[5] Tao W,Jin T,Bin L.Blind Detection of Region Duplication Forgery by Merging Blur and Affine Moment Invariants[C]∥2013 Seventh International Conference on Image and Graphics.2013:258-264
[6] 左菊仙,刘本永.伪造图像典型篡改操作的检测[J].中国图象图形学报,2012,17(11):1367-1375
[7] Pan X Y,Lyu S W.Region duplication detection using image feature matching[J].IEEE Transactions on Information Forensics and Security,2010,5(4):857-867
[8] Jaberi M,Bebis G,Hussain M,et al.Accurate and robust localization of duplicated region in copy-move image forgery[J].Machine Vision and Applications,2014,25(2):451-475
[9] Muhammad G,Muhammad H,Khawaji K,et al.Blind copy moveimage forgery detection using dyadic undecimated wavelet transform[C]∥17th International Conference on Digital Signal Processing.2011:1-6
[10] Muhammad G,Muhammad H,Bebis G.Passive copy move image forgery detection using undecimated dyadic wavelet transform[J].Digital Investigation,2012,9(1):49-57
[11] Shao H,Yu T S,Xu M J,et al.Image region duplication detection based on circular window expansion and phase correlation[J].Forensic Science International,2012,222(1/3):71-82
[12] Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110
[13] 刘笑楠,苑玮琦,张波.一种虹膜色素块检测与分类方法[J].沈阳工业大学学报,2014,6:688-693

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed