广西师范大学学报(自然科学版) ›› 2012, Vol. 30 ›› Issue (3): 135-141.

• • 上一篇    下一篇

基于DCT特征点的感知图像Hash函数

唐振军, 戴玉敏, 张显全, 张师超   

  1. 广西师范大学计算机科学与信息工程学院,广西桂林541004
  • 收稿日期:2012-05-18 出版日期:2012-09-20 发布日期:2018-12-04
  • 通讯作者: 唐振军(1979—),男,广西桂平人,广西师范大学副教授,博士。E-mail:tangzj230@163.com
  • 作者简介:唐振军,男,1979年生,汉族,广西桂平人,广西师范大学计算机科学与信息工程学院副教授,硕士生导师,博士。研究方向为图像处理与多媒体信息安全。
  • 基金资助:
    国家863计划项目(2012AA011005);澳大利亚ARC国家基金资助项目(DP0985456);国家自然科学基金资助项目(61165009,61170131);广西自然科学基金创新研究团队项目(2012GXNSFGA060004);广西自然科学基金资助项目(2012GXNSFBA053166,2011GXNSFD018026,0832104);广西科学研究与技术开发计划项目(桂科攻10123005-8);广西师范大学博士科研启动基金资助项目

Perceptual Image Hash Function Using DCT-Based Feature Points

TANG Zhen-jun, DAI Yu-min, ZHANG Xian-quan, ZHANG Shi-chao   

  1. College of Computer Science and Information Technology,GuangxiNormal University,Guilin Guangxi 541004,China
  • Received:2012-05-18 Online:2012-09-20 Published:2018-12-04

摘要: 本文提出一种基于离散余弦变换(DCT)特征点的感知图像Hash函数算法。具体地说,先对输入图像预处理,生成规范化图像。在此基础上,将规范化图像分块并进行二维DCT处理,利用DCT交流系数构造特征点。最后计算特征点的重心,用特征点与重心的欧氏距离生成Hash。实验结果表明本文算法对正常数字处理稳健并具有良好的唯一性。接收机操作特性曲线对比发现,本文算法性能优于3种现有的算法。

关键词: 图像Hash, Hash函数, 图像检索, 拷贝检测, 接收机操作特性

Abstract: This paper proposes a perceptual image hash function using discrete cosine transform (DCT) based feature points.Specifically,the input image is first mapped to a normalized image by preprocessing.The normalized image is then divided into non-overlapping blocks.Next,two dimensional DCT is applied toeach block,and AC coefficients of each block are used to form a feature point.Finally,gravity center of the feature points is calculated and the hash is obtained by computing the Euclidian distance between the gravity center and each feature point.Experiments show that the proposed algorithm is robust against normal digital operations and reaches good discrimination.Receiver operating characteristics (ROC) curve comparisons indicate that the proposed algorithm outperforms three well-known existing algorithms.

Key words: Image hash, hash function, image retrieval, copy detection, receiver operating characteristics (ROC)

中图分类号: 

  • TP391.411
[1] VENKATESAN R,KOON S,JAKUBOWSKI M,et al.Robust image hashing[C]//Proceedings of IEEE International Conference on Image Processing.Los Alamitos,CA:IEEE Computer Society,2000:664-666.
[2] LIN Ching-yung,CHANG Shih-fu.A robust image authentication method distinguishing JPEG compression from malicious manipulation[J].IEEE Transactions on Circuits and Systems for Video Technology,2001,11(2):153-168.
[3] LEFEBVRE F,MACQ B,LEGA J D.RASH:Radon Soft Hash algorithm[C]//Proceedings of European Signal Processing Conference.Toulouse,France:TESA,2002:299-302.
[4] De ROOVER C,De VLEESCHOUWER C,LEFEBVRE F,et al.Robust video hashing basedon radial projections of key frames[J].IEEE Transactions On Signal Processing,2005,53(10):4020-4037.
[5] KOZAT S S,VENKATESAN R,MIHCAK K.Robust perceptual image hashingvia matrixinvariants[C]//Proceedings of IEEE International Conference on Image Processing.Los Alamitos,CA:IEEE Computer Society,2004:3443-3446.
[6] MONGA V,MIHCAK M K.Robust and secure image hashing via non-negative matrixfactorizations[J].IEEE Transactions on Information Forensics and Security,2007,2(3):376-390.
[7] TANG Zhen-jun,WANG Shuo-zhong,ZHANG Xin-peng,et al.Robust imagehashing fortamper detection using non-negative matrix factorization[J].Journal of Ubiquitous Convergence and Technology,2008,2(1):18-26.
[8] OU Yang,RHEE K H.A key-dependent secure image hashing scheme by using Radontransform[C]//Proceedings of the IEEE International Symposium on IntelligentSignal Processing and Communication Systems.Los Alamitos,CA:IEEE Computer Society,2009:595-598.
[9] 唐振军,魏为民,张新鹏,等.用于图像检索的稳健Hash[J].东南大学学报:自然科学版,2007,37(S1):105-108.
[10] 唐振军,王朔中,魏为民,等.用于图像Hash的视觉相似度客观评价测度[J].中国图象图形学报,2008,13(10):2040-2043.
[11] TANG Zhen-jun,WANG Shuo-zhong,ZHANG Xin-peng,et al.Structuralfeature-basedimage hashing and similarity metric for tampering detection[J].Fundamenta Informaticae,2011,106(1):75-91.
[12] PETITCOLAS F A P.Watermarking schemes evaluation[J].IEEE SignalProcessing Magazine,2000,17(5):58-64.
[13] FAWCETT T.An introduction to ROC analysis[J].Pattern Recognition Lettrs,2006,27(8):861-874.
[1] 唐振军. 基于PCA特征距离的图像哈希算法[J]. 广西师范大学学报(自然科学版), 2016, 34(4): 9-18.
[2] 马媛媛, 吕康, 徐久成. 基于粒计算多层次结构相似度的图像检索[J]. 广西师范大学学报(自然科学版), 2013, 31(3): 127-131.
[3] 李志欣, 陈宏朝, 吴王景莉, 周生明. 基于概率主题建模的图像语义学习与检索[J]. 广西师范大学学报(自然科学版), 2012, 30(3): 125-134.
[4] 李双群, 徐久成, 张灵均, 李晓艳. 基于相容粒的彩色图像检索算法[J]. 广西师范大学学报(自然科学版), 2011, 29(3): 173-178.
[5] 罗辛, 潘乔, 王洪亚, 陈美, 北研二. 基于SOFM的高速图像检索算法实现[J]. 广西师范大学学报(自然科学版), 2011, 29(2): 180-184.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报(自然科学版)编辑部
地址:广西桂林市三里店育才路15号 邮编:541004
电话:0773-5857325 E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发