抗裁剪和平移攻击的图像拷贝检测算法

Image Copy Detection Scheme Against Cropping and Translation Attacks

有效判定经拷贝攻击之后图像的版权归属是当今图像拷贝检测研究的热点和难点之一.现有的检测算法对于噪声、拉伸、旋转、等比缩放等常见攻击具有较好的鲁棒性,而对于裁剪、平移攻击则比较脆弱.针对上述问题,提出一种基于SIFT局部特征和整体DCT系数顺序测度的图像拷贝检测算法.该算法首先通过匹配的SIFT特征划定内容保持不变的区域,然后对内容不变区域的亮度分量作整体DCT变换,并将DCT系数低频交流成分的顺序测度作为图像特征,最后通过该特征判定拷贝是否存在.由于匹配的SIFT特征可以精确定位拷贝发生区域,因而对裁剪、平移攻击具有较好的抵抗能力,又由于引入整体DCT系数顺序测度作为特征,因而可以很好地抵抗其他常见攻击.同时提出翻转补偿策略,使本算法能抵抗水平翻转和垂直翻转攻击.实验结果证明,在抵抗裁剪和平移攻击方面,给出的算法相对于已有算法具有较高的查准率和查全率.

To effectively detect copyrighted images suffering from copy attacks is one of the hotspots and difficulties in the image copy detection research. Currently, most of copy detection algorithms can successfully resist the common attacks, such as noise, scale, rotation and so on, but they are quite fragile to cropping and translation attacks. In this paper, an image copy detection algorithm based on SIFT features and ordinal measure of the full DCT coefficients is proposed. The algorithm firstly extracts the same content regions from target image and query image based on matched SIFT features; Secondly, the ordinal measures of the low frequency DCT coefficients in the same content regions are used as the image signatures; Finally the image signatures are used to detect the image copies. The matched SIFT features can locate copy regions accurately, so the proposed algorithm can resist cropping and translation attacks. Meanwhile, the ordinal measure of full DCT coefficients is introduced to resist common attacks. Moreover, the flipping compensation strategy used in this algorithm can resist the horizontal and vertical flipping attacks. The experimental results show that he algorithm has higher precision and recall rate than the existing methods in terms of cropping and translation attacks.