Localization of Copy-Move Forgery in Digital Images through Differential Excitation Texture Features

Abstract

In this digital age, the extensive usage of digital devices and availability of open source image editing software leads to the easy manipulation of digital images. Copy-Move Forgery (CMF) is a guileless and widespread approach to hide or duplicate a certain portion of the image without leaving visual clues. Thus, it is difficult to detect the copy-move forgeries and there is a need for forensic experts to rely on an effective approach for CMF detection for forensic analysis. Hence, an efficient passive block based approach to detect and localize CMF is proposed. In the proposed method, texture features are extracted from Differential Excitation Component on the overlapping blocks of the image. Similarity measure is performed for block matching and mapping is done to identify the duplicated regions. Evaluation is performed qualitatively and quantitatively on CoMoFoD dataset; true detection rate of 0.99 and false detection rate of 0.08 has been achieved. Evaluation validates that proposed method out performs the other existing methods with regard to detection accuracy.

International Journal of Electronics and Telecommunications

“…The colour image was converted to gray image [10]and then normalized in the range [0, 1]. Lanes markings have values closer to 1 and the black and gray road surfaces have low values closer to 0.An appendix may be included (and is often helpful) in mathematical or computational modeling.…”

“…Consider the image is shown in Figure .2, with set sample of detected edge point co-ordinates as (xi, yj) = (6,5), (7,6), (7,16), (8,15), (9,14), (10,13), (13,11), (14,10), (15,9), (16,8) and (17,7).…”

Weber Law Based Approach for Multi-Class Image Forgery Detection

“…Information in an image is based on its objects' or edge that are formulated as boundaries of objects [4]. Texture information is the most crucial information in a picture that should be examined for image validation, detection, and localization of Copy-Move forgeries [5]. Image contains a different type of extra information that can be removed using different preprocessing of an image for a better understanding of image texture [2].…”

“…COMFORD v.0, CASIA 1.0, CASIA 2.0, CASIA TIDE, DVMM, and Columbia were used for the performance evaluation of the proposed description algorithm. Suresh et al [5] detected Copy-Move forgery using changes in color and texture information of an image. The firefly algorithm worked well to find a relationship between color fusion and the texture of tempered regions in an image.…”

“…The proposed technique performed 97% accurately on CASIA 1.0 and ComFodv.0 image database applied for experimentation. Suresh et al [25] used texture information to detect Copy-Move forgery. Texture information was obtained by isolating an image into overlapping blocks and finding differential excitation of image blocks.…”