摘要
针对现有翻拍图像鉴别算法辨别理论基础弱和鉴别率不高的问题,提出了基于局部平面线性点的翻拍图像鉴别算法。首先建立图像成像过程的数学模型,然后从模型中提出局部平面线性点的概念和性质,根据性质提取图像中的局部平面线性点作为特征值;最后利用支持向量机分类器对真实图像和翻拍图像进行分类。实验结果及分析表明:本文算法不但对翻拍图像具有较好的鉴别率,并且特征向量的维数也低于其他鉴别算法。
In order to solve the problem that the existing recaptured image algorithms have weak theoretical basis and low forensics rate,a new recaptured image identifying algorithm is put forward based on local plane linear point. Firstly,the proposed algorithm establishes the mathematical model in the imaging process,and provides concepts and properties of the local plane linear point from the model. Then the local plane linear point was extracted from image as the characteristic value. Finally the support vector machine is applied to classify the recaptured image with the characteristic value. The results show the proposed method can not only identify the recaptured image but also have better identification rate,and the dimension of the characteristic vector is also lower than those obtained by other algorithms.
引文
[1]Gao X,Qiu B,Shen J J,et al.A smart phone image database for single image recapture detection[C]?The9th International Conference on Digital Watermarking,Seoul,Korea,2010:90-104.
[2]Yu H,Ng T T,Sun Q B,et al.Recapture photo detection using specularity distribution[C]?IEEE International Conference on Image Processing,San Diego,USA,2008:3140-3143.
[3]Cao H,Alex C K,et al.Identification of recaptured photographs on LCD screens[C]?IEEE International Conference on Acoustics,Speech,and Signal Processing,Dallas,USA,2010:1790-1793.
[4]Ng T T,Chang S F,Jessie H,et al.Physics-motivated features for distinguishing photographic images and computer graphics[C]?The 13th Annual ACMInternational Conference on Multimedia,Singapore,Singapore,2005:239-248.
[5]Liu Hua-cheng,Wang Rang-ding.Recaptured image detection based on DCT coefficients[J].Journal of Computational Information Systems,2013,9(20):8139-8145.
[6]Gao X T,Ng T T,Qiu B,et al.Single-view recaptured image detection based on physics based features[C]?IEEE International Conference on Multimedia and Expo,Suntec,Singapore,2010:1469-1474.
[7]Ke Yong-zhen,Shan Qing-qing,Qin Fan,et al.Image recaptured detection using multiple features[J].International Journal of Multimedia and Ubiquitous Engineering,2013,8(5):71-82.
[8]Ojala T,Pietikainen M,Maenpaa T,et al.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[9]黄维,黄添强,张雪莉,等.基于块效应网格偏移的重获取JPEG图像篡改检测[J].网络与信息安全学报,2017,3(12):24-30.Huang Wei,Huang Tian-qiang,Zhang Xue-li,et al.JPEG recapture image tamper detection method based on block effect grid offset[J].Chinese Journal of Network and Information Security,2017,3(12):24-30.
[10]Faridy H,Lyu S,et al.Higher-order wavelet statistics and their application to digital forensics[C]?IEEE Workshop on Statistical Analysis in Computer Vision,Madison,USA,2003:1-8.
[11]卢燕飞,冯莉,李兴华,等.基于图像表面梯度的翻拍检测[J].北京交通大学学报,2012,36(5):57-61.Lu Yan-fei,Feng Li,Li Xing-hua,et al.Recaptured image detection based on surface gradient[J].Journal of Beijing Jiaotong University,2012,36(5):57-61.
[12]冯莉.基于数字图像镜面反射和表面梯度的翻拍取证研究[D].北京:北京交通大学电子信息工程学院,2013.Feng Li.Blind forensics of recaptured image based on specularity distribution and surface gradient[D].Beijing:College of Electronic Information Engineering,Beijing Jiaotong University,2013.
[13]Ng T T,Chang S F,et al.Using geometry invariants for camera response function estimation[C]?IEEE Conference on Computer Vision and Pattern Recognition,Minneapolis,USA,2007:1-8.
[14]Gonzalez R C,Woods R E,等.数字图像处理[M].北京:电子工业出版社,2011:349-394