摘要
为解决传统图像拼接检测算法对图像内容、光照变化等鲁棒性不强问题,提出一种基于多种纹理特征融合的图像拼接检测方法。对二维灰度图像执行非下采样轮廓波变换(NSCT),以获得包含图像纹理特征的一系列子带图像。对在水平和垂直方向进行差分处理的低频子带图像以及4个高频图像,获取韦伯局部描述符(WLD)纹理和局部三值模式(LTP)纹理。将WLD纹理与灰度共生矩阵结合,得到像素点强度、梯度与灰度之间的关系;再将LTP纹理与灰度共生矩阵结合,得到无噪声和光照影响的像素点灰度间关系;最后分别提取WLD值共生矩阵和LTP值共生矩阵的对比度、相关性、相异度、熵、能量等5个特征,并融合成特征向量,使用RBF神经网络分类。该方法在哥伦比亚彩色图像库上检测准确率达到了95.7%。
Aiming at the problem that traditional image splicing detection algorithm is not robust to image content and illumination change,an image splicing detection method based on multi-texture feature fusion is proposed.In this method,non-subsampling contour wave transform(NSCT)is performed on two-dimensional gray images to obtain a series of sub-band images with image texture features.Then the low frequency sub-band images were processed in the horizontal and vertical directions,and the four high frequency images were used to obtain the Weber local descriptor(WLD)texture and local three-valued model(LTP)texture.Then WLD texture and gray level co-occurrence matrix are combined to obtain the relationship among pixel intensity,gradient and grayscale;LTP texture and grayscale co-occurrence matrix are combined to obtain the relationship among the noiseless pixels affected by light.Finally the five features including WLD value symbiosis matrix,LTP co-occurrence matrix phase contrast ratio,correlation,entropy and energy are extracted and integrated into feature vectors.RBF neural network is employed for classification.
引文
[1]张震,边玉琨,康吉全,等.一种新的拼接图像检测方法[J].计算机应用研究,2009,26(3):1127-1130.
[2]陈园园,于在河.数字图像被动取证技术综述[J].吉林大学学报:信息科学版,2014,32(6):689-698.
[3]石泽男.基于局部纹理特征的数字图像拼接盲鉴别算法研究[D].长春:吉林大学,2017.
[4]MUHAMMAD H,SAHAR Q,GEORGE B,et al.Evaluation of image forgery detection using multi-scale Weber local descriptors[J].Artificial Intelligence Tools,2015,24(4):416-417.
[5]VERMA M,RAMAN B.Local tri-directional patterns:a new texture feature descriptor for image retrieval[J].Digital Signal Processing,2016,51:62-72.
[6]HASHMI M F,KESKAR A G.Image forgery authentication and classification using hybridization of HMM and SVM classifier[J].International Journal of Security&Its Applications,2015,9(4):125-140.
[7]李燕,钟磊,李健.基于LBP和共生矩阵的图像拼接篡改检测[J].武汉大学学报:理学版,2015,61(6):517-524.
[8]JIN H,LIU Q,LU H,et al.Face detection using improved LBP under Bayesian framework[C].IEEE First Symposium on Multi-Agent Security and Survivability,2004:306-309.
[9]TAN X,XU T,TAN X,et al.Enhanced local texture feature sets for face recognition under difficult lighting conditions[J].IEEE Transactions on Image Processing,2010,19:1635-1650.
[10]JALA T,PETIKAINEN M,MAENPAA T.Multiresolution gray scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[11]CHEN J,SHAN S G,HE C,et al.WLD:a robust local image descriptor[J].IEEE TPAMI,2010,32(9):1705-1719.
[12]JAIN A K.Fundamentals of digital signal processing[M].New Jersy:Prentice-Hall,1986.
[13]朱正礼,赵春霞,侯迎坤,等.基于多特征的旋转不变纹理图像检索[J].南京理工大学学报,2012,36(3):375-380.
[14]雷升锴,刘红阳,何嘉,等.动态K-均值聚类算法在RBF神经网络中心选取中的应用[J].信息系统工程,2011(6):83-85.
[15]王奇平,王祯璋.基于径向基神经网络的变压器故障诊断方法研究[J].电力与能源,2017,38(5):546-548.
[16]COLUMBIA DVMM RESEARCH LAB.Columbia image splicing detection evaluation dataset[EB/OL].http://www.ee.columbia.edu/ln/dvmm/downloads/authsplcuncmp/.
[17]王任华,霍宏涛,蒋敏.RANSAC算法在同图复制鉴定中的应用研究[J].计算机应用研究,2014,31(7):2209-2211.