Identifying natural images and computer generated graphics based on binary similarity measures of PRNU
Identifying natural images and computer generated graphics based on binary similarity measures of PRNU
复制标题
基于 PRNU 的二元相似性度量识别自然图像和计算机生成的图形
DOI：
10.1007/s11042-017-5101-3
复制
发表时间：
2019-01-01
影响因子：
3.6
通讯作者：
Zhu, Yin
中科院分区：
文献类型：
--
作者：
Long, Min;Peng, Fei;Zhu, Yin
针对自然图像和计算机生成图形的识别问题，提出了一种基于PRNU（photoresponse non-uniformity）二值相似性度量的图像源管道取证方法。由于PRNU是自然图像的一个独特属性，PRNU的二进制相似性度量被用来表示自然图像和计算机生成图形之间的差异。从RGB三通道的PRNU中计算二值Kullback-Leibler距离、二值最小直方图距离、二值绝对直方图距离和二值互熵。LIBSVM共有36个维度的特征，用于分类。实验结果和分析表明，该方法的平均识别准确率可达99.83%，并且在自然图像和计算机生成图形的识别能力上取得了平衡。同时，它对JPEG压缩、旋转和加性噪声具有较好的鲁棒性。
Aiming at the identification of natural images and computer generated graphics, an image source pipeline forensics method based on binary similarity measures of PRNU (photo response non-uniformity) is proposed. As PRNU is a unique attribute of natural images, binary similarity measures of PRNU are used to represent the differences between natural images and computer generated graphics. Binary Kullback-Leibler distance, binary minimum histogram distance, binary absolute histogram distance and binary mutual entropy are calculated from PRNU in RGB three channels. With a total of 36 dimensions of features, LIBSVM is used for classification. Experimental results and analysis indicate that it can achieve an average identification accuracy of 99.83%, and the capability of identifying natural images and computer generated graphics is balanced. Meanwhile, it is robust against JPEG compression, rotation and additive noise.