Robust Image Hashing via Random Gabor Filtering and DWT

作     者：Zhenjun Tang Man Ling Heng Yao Zhenxing Qian Xianquan Zhang Jilian Zhang Shijie Xu 

作者机构：Guangxi Key Lab of Multi-Source Information Mining&SecurityGuangxi Normal UniversityGuilin541004China Shanghai Institute of Intelligent Electronics&SystemsSchool of Computer ScienceFudan UniversityShanghai200433China School of Information SystemsSingapore Management University178902Singapore 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2018年第55卷第5期

页      面：331-344页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work is partially supported by the National Natural Science Foundation of China(Nos.61562007,61762017,61702332) National Key R&D Plan of China(2018YFB1003701) Guangxi“Bagui Scholar”Teams for Innovation and Research,the Guangxi Natural Science Foundation(Nos.2017GXNSFAA198222,2015GXNSFDA139040) the Project of Guangxi Science and Technology(Nos.GuiKeAD17195062) the Project of the Guangxi Key Lab of Multi-source Information Mining&Security(Nos.16-A-02-02,15-A-02-02) the Guangxi Collaborative Innovation Center of Multi-source Information Integration and Intelligent Processing,and the Innovation Project of Guangxi Graduate Education(No.XYCSZ 2018076) 

主　　题：Image hashing Gabor filtering chaotic map skew tent map discrete wavelet transform. 

摘      要：Image hashing is a useful multimedia technology for many applications,such as image authentication,image retrieval,image copy detection and image *** this paper,we propose a robust image hashing based on random Gabor filtering and discrete wavelet transform(DWT).Specifically,robust and secure image features are first extracted from the normalized image by Gabor filtering and a chaotic map called Skew tent map,and then are compressed via a single-level 2-D *** hash is finally obtained by concatenating DWT coefficients in the LL *** experiments with open image datasets are carried out and the results illustrate that our hashing is robust,discriminative and *** operating characteristic(ROC)curve comparisons show that our hashing is better than some popular image hashing algorithms in classification performance between robustness and discrimination.