基于量化颜色特征和SURF检测器的图像盲鉴别算法

计算机科学 ›› 2019, Vol. 46 ›› Issue (11A): 268-272.

基于量化颜色特征和SURF检测器的图像盲鉴别算法

胡梦琪^1,2, 郑继明¹

(复杂系统智能分析与决策重庆市高校重点实验室重庆400065)¹;
(重庆邮电大学计算机科学与技术学院重庆400065)²

出版日期:2019-11-10 发布日期:2019-11-20
通讯作者: 郑继明(1963-),男,硕士,教授,主要研究方向为小波分析、数字图像处理等,E-mail:zhengjm@cqupt.edu。
作者简介:胡梦琪(1994-),女,硕士生,主要研究方向为数字图像处理,E-mail:yolandahumq@qq.com。

Blind Image Identification Algorithm Based on HSV Quantized Color Feature and SURF Detector

HU Meng-qi^1,2, ZHENG Ji-ming¹

(Key Lab of Intelligent Analysis and Decision on Complex Systems,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)¹;
(School of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)²

Online:2019-11-10 Published:2019-11-20

摘要/Abstract

摘要： 针对现有图像复制粘贴篡改检测中提取的特征对于彩色图像内容描述不全面且匹配时间过长的问题,研究了运用量化颜色特征和SURF检测器的数字图像盲鉴别算法。该算法在特征提取过程中将HSV模糊量化颜色特征和SURF检测器结合,形成全面描述彩色图像内容的FCQ-SURF特征,并在特征匹配阶段将K-Means聚类和KNN方法结合来提高匹配效率。实验结果显示,在CASIA 1.0和FAU彩色图像测试库上,所提算法能很好地检测和定位彩色图像的复制粘贴篡改,在图像的多重篡改攻击和多区域篡改方面也得到了很好的检测效果。实验数据结果说明,该算法对彩色图像复制粘贴篡改检测的正确率较高,且匹配时间较有优势。

关键词: FCQ-SURF特征, K-Means聚类匹配, 复制粘贴篡改, 图像盲鉴别

Abstract: Aiming at the problem that the features extracted from the color image by existing copy-move forgery detection (CMFD) algorithms are not comprehensive and the matching time is too high,the blind identification algorithm for digital images by using quantized color features and SURF detector was studied.In the feature extraction process,the algorithm combines HSV fuzzy quantization color feature and SURF feature to form a comprehensive description,called the FCQ-SURF features,of color image content.K-Means clustering and KNN method are used to improve matching efficiency in feature matching stage.The experimental results show that the algorithm can detect and locate the colorima-ge copy-move forgery well in CASIA 1.0 and FAU color image test library.It also has a good detection effect for multiple tampering attacks and multi-region tampering of images.The experimental results demonstrate that the proposed algorithm has higher detection accuracy and better matching time for color image copy-move forgery.

Key words: Blind image identification, Copy-move forgery, FCQ-SURF features, K-Means clustering matching

中图分类号:

TP391.4

胡梦琪, 郑继明. 基于量化颜色特征和SURF检测器的图像盲鉴别算法[J]. 计算机科学, 2019, 46(11A): 268-272. https://doi.org/

HU Meng-qi, ZHENG Ji-ming. Blind Image Identification Algorithm Based on HSV Quantized Color Feature and SURF Detector[J]. Computer Science, 2019, 46(11A): 268-272. https://doi.org/

参考文献

[1]SONI B,DAS P K,THOUNAOJAM D M.CMFD:a detailed review of block based and key feature based techniques in image copy-move forgery detection[J].Iet Image Processing,2018,12(2):167-178.
[2]MALVIYA A V,LADHAKE S A.Pixel Based Image Forensic Technique for Copy-move Forgery Detection Using Auto Color Correlogram[J].Procedia Computer Science,2016,79:383-390.
[3]GONG J C,GUO J C.Image Copy-Move Forgery Detection Using SURF in Opponent Color Space[J].Transactions of Tianjin University,2016,22(2):151-157.
[4]ZHU Y,SHEN X J,CHEN H P.Covert Copy-move ForgeryDetection Based on Color LBP[J].Acta Automatica Sinica,2017,43(3):390-397.
[5]WANG X Y,JIAO L X,WANG X B,et al.A new keypoint-based copy-move forgery detection for color image[J].Applied Intelligence,2018:1-23.
[6]谢伟,万晓霞,叶松涛,等.基于局部色彩不变量的图像篡改检测方法[J].湖南大学学报(自科版),2016,43(8):128-134.
[7]KUSHOL R,SALEKIN M S,KABIR M H,et al.Copy-MoveForgery Detection Using Color Space and Moment Invariants-Based Features[C]∥International Conference on Digital Image Computing:Techniques and Applications.IEEE,2016:1-6.
[8]BAY H,TUYTELAARS T,GOOL L V.SURF:Speeded up robust features[C]∥Proceedings of the 9th European conference on Computer Vision- Volume Part I.Berlin:Springer,2006.
[9]王梦思,王任华.基于SIFT和RGB特征的同图复制篡改检测算法[J].中国人民公安大学学报(自然科学版),2018,24(2):83-87.
[10]CHERNOV V,ALANDER J,BOCHKO V.Integer-based accurate conversion between RGB and HSV color spaces[J].Computers & Electrical Engineering,2015,46:328-337.
[11]徐慧英,袁杰,赵建民,等.一种基于颜色和纹理的图像检索方法[J].计算机科学,2009,36(5):282-286.
[12]TAHOUN M A,NAGATY K A,EL-ARIEF T I.A Robust Content-Based Image Retrieval System Using Multiple Features Representations[C]∥Networking,Sensing & Control.IEEE,2005:116-122.
[13]居学尉,贺利军,朱光宇.基于离散Fréchet距离的多目标优化方法[J].计算机集成制造系统,2017(2):253-260.
[14]陈付幸,王润生.基于预检验的快速随机抽样一致性算法[J].软件学报,2005,16(8):1431-1437.
[15]王天召,徐克虎,陈金玉.基于K-means聚类和RANSAC的图像配准算法研究[J].计算机工程与科学,2014,36(9):1765-1769.
[16]PENG J,HEISTERKAMP D R,DAI H K.Adaptive Discriminant and Quasiconformal Kernel Nearest Neighbor Classification[M]∥Support Vector Machines:Theory and Applications.Berlin:Springer,2005.
[17]李若晨,李若晨,李勤,等.图像内部Move-Copy篡改盲取证算法研究[J].四川大学学报(自然科学版),2016,53(1):67-72.
[18]申铉京,朱叶,吕颖达,等.基于SIFT和HSI模型的彩色图像复制-粘贴盲鉴别算法[J].吉林大学学报(工学版),2014,44(1):171-176.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed