摘要
针对现有遥感影像感知哈希认证算法存在的鲁棒性不足的问题,本文利用PCNN在边缘检测过程中能够抑制噪声的特点,提出一种基于自适应PCNN与PCA的遥感影像感知哈希认证算法.首先,对遥感影像进行四边形隐形格网划分之后,根据格网单元的信息熵自适应地决定PCNN的时间衰减参数.然后,通过PCNN提取格网单元的边缘特征,进而构造格网单元的特征矩阵.接下来,对特征矩阵进行基于PCA和信息熵的自适应摘要化,得到的序列进行加密处理后就是该格网单元的感知哈希序列.实验表明,该算法在保持篡改敏感性的同时,对无损压缩和LSB水印嵌入具有近乎100%的鲁棒性,对有损压缩的鲁棒性在95%以上,相比于现有算法有了较大提高.
Due to the disadvantage of the existing perceptual hash algorithm for remote sensing image has,a perceptual hash algorithm based on adaptive PCNN and PCA for remote sensing image authentication is proposed making use of the characteristic PCNN can suppress noise during edge detection. Firstly,gird division is applied on the remote sensing image,and the parameter of decay time is adaptively defined based on the entropy of the grid. Secondly,the edge feature of each grid is detected by the PCNN,and the feature matrix of the grid is then constructed. Thirdly,the feature matrix is adaptively summarized based on PCA and grid entropy,the result is then encrypted to generate the perceptual hash value of the grid. The experiment results show that the robustness of the algorithm is greatly improved while it is sensitive to malicious tamper of the remote sensing image:it can keep nearly 100% robust to lossless compression and LSB watermark embedding,and can keep more than 95% robust to lossy compression.
引文
[1] LEI J,HAN Z,VAZQUEZ-CASTRO M A,et al.Secure satellite communication systems design with individual secrecy rate constraints[J].IEEE transactions on information forensics and security,2011,6(3):661-671.
[2] 牛夏牧,焦玉华.感知哈希综述[J].电子学报,2008,36(7):1405-1411.
[3] 付剑晶,王珂,徐建军.一种面向多波段数字遥感影像的版权保护方案[J].电子学报,2016,44(3):732-739.
[4] 丁凯孟,朱颖婷,朱长青,等.基于Gabor滤波器组与DWT的遥感影像感知哈希认证算法[J].铁道学报,2016,38(7):70-76.
[5] WANG K,TANG J,WANG N,et al.Semantic boosting cross-modal hashing for efficient multimedia retrieval[J].Information sciences,2016,330:199-210.
[6] ZOU F,CHEN Y,SONG J,et al.Compact image fingerprint via multiple Kernel hashing[J].IEEE transactions on multimedia,2015,17(7):1006-1018.
[7] SUN R,ZENG W.Secure and robust image hashing via compressive sensing[J].Multimedia tools and applications,2014,70:1651-1665.
[8] OUYANG J,COATRIENX G,SHU H.Robust hashing for image authentication using quaternion discrete Fourier transform and log-polar transform[J].Digital signal processing,2015,41:98-109.
[9] HAN M,YANG X,JIANGg E.An extreme learning machine based on cellular automata of edge detection for remote sensing images[J].Neurocomputing,2016,198:27-34.
[10] 周立国,冯学智,肖鹏峰,等.一种频域高分辨率遥感图像线状特征检测方法[J].测绘学报,2011,40(3):312-317.
[11] GU J,PAN Y,WANG H.Research on the improvement of image edge detection algorithm based on artificial neural network[J].Optik-international journal for light and electron optics,2015,126(21):2974-2978.
[12] HELMY A K,EL-TAWEEL G S.Image segmentation scheme based on SOM-PCNN in frequency domain[J].Applied soft computing,2016,40:405-415.
[13] YANG Z,DONG M,GUO Y,et al.A new method of micro-calcifications detection in digitized mammograms based on improved simplified PCNN[J].Neurocomputing,2016,218:79-90.
[14] ALA R.A new automatic parameter setting method of a simplified PCNN for image segmentation[J].IEEE transactions on neural networks,2011,22(6):880-892.
[15] LIU S,HE D,LIANG X.An improved hybrid model for automatic salient region detection[J].IEEE signal processing letters,2012,19(4):207-210.
[16] 邵晓鹏,钟宬,王杨,等.一种简化PCNN模型在彩色图像边缘检测上的应用[J].西安电子科技大学学报(自然科学版),2012,39(6):1-9.
[17] PORTNOY I,MELENDEZ K,PINZON H,et al.An improved weighted recursive PCA algorithm for adaptive fault detection[J].Control engineering practice,2016,50:69-83.
[18] DELCHAMBRE L.Weighted principal component analysis:a weighted covariance eigendecomposition approach[J].Monthly notices of the royal astronomical society,2014,446(4):3545-3555.