Image Splicing Detection Based on Texture Features with Fractal Entropy

作     者：Razi J.Al-Azawi Nadia M.G.Al-Saidi Hamid A.Jalab Rabha W.Ibrahim Dumitru Baleanu 

作者机构：Department of Laser and Optoelectronics EngineeringUniversity of TechnologyBaghdad10066Iraq Department of Applied SciencesUniversity of TechnologyBaghdad10066Iraq Department of Computer System and TechnologyFaculty of Computer Science and Information TechnologyUniversiti MalayaKuala Lumpur50603Malaysia IEEE:94086547Kuala Lumpur59200Malaysia Department of MathematicsCankaya UniversityBalgat06530AnkaraTurkey Institute of Space SciencesR76900 Magurele-BucharestRomania Department of Medical ResearchChina Medical UniversityTaichung40402Taiwan 

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

年 卷 期：2021年第69卷第12期

页      面：3903-3915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 research was funded by the Faculty Program Grant(GPF096C-2020) University of Malaya Malaysia 

主　　题：Fractal entropy image splicing texture features LBP SVM 

摘      要：Over the past years,image manipulation tools have become widely accessible and easier to use,which made the issue of image tampering far more *** a direct result to the development of sophisticated image-editing applications,it has become near impossible to recognize tampered images with naked ***,to overcome this issue,computer techniques and algorithms have been developed to help with the identification of tampered *** on detection of tampered images still carries great *** the present study,we particularly focus on image splicing forgery,a type of manipulation where a region of an image is transposed onto another *** proposed study consists of four features extraction stages used to extract the important features from suspicious images,namely,Fractal Entropy(FrEp),local binary patterns(LBP),Skewness,and *** main advantage of FrEp is the ability to extract the texture information contained in the input ***,the“support vector machine(SVM)classification is used to classify images into either spliced or *** analysis shows that the proposed algorithm performs better than recent state-of-the-art of splicing detection ***,the proposed algorithm achieves an ideal balance between performance,accuracy,and efficacy,which makes it suitable for real-world applications.