Copy-Move Forgery Detection Technique for Forensic Analysis in Digital Images

Abstract

Due to the powerful image editing tools images are open to several manipulations; therefore, their authenticity is becoming questionable especially when images have influential power, for example, in a court of law, news reports, and insurance claims. Image forensic techniques determine the integrity of images by applying various high-tech mechanisms developed in the literature. In this paper, the images are analyzed for a particular type of forgery where a region of an image is copied and pasted onto the same image to create a duplication or to conceal some existing objects. To detect the copy-move forgery attack, images are first divided into overlapping square blocks and DCT components are adopted as the block representations. Due to the high dimensional nature of the feature space, Gaussian RBF kernel PCA is applied to achieve the reduced dimensional feature vector representation that also improved the efficiency during the feature matching. Extensive experiments are performed to evaluate the proposed method in comparison to state of the art. The experimental results reveal that the proposed technique precisely determines the copy-move forgery even when the images are contaminated with blurring, noise, and compression and can effectively detect multiple copy-move forgeries. Hence, the proposed technique provides a computationally efficient and reliable way of copy-move forgery detection that increases the credibility of images in evidence centered applications.

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

“…Proposed DETF method is capable of detecting multiple forged regions and also is able to detect large circular, rectangular and irregular forged regions. The simulation results demonstrate that proposed method is superior to other CMF detection methods [3,4,7,12,16,[19][20][21][22] in terms of detection rate and outperforms other methods [3,4,7,12,16,19] with regard to computational complexity.…”

“…• Phase #2: In this phase of experiments, our attention is on to assess the robustness of proposed method against various post-processing attacks. • Phase #3: In this phase of experiments, we concentrated on comparative analysis of proposed method with existing methods reported in the literature [3,4,7,12,16,[19][20][21][22].…”

“…Here, the comparative analysis of proposed DETF method with other state of art methods is presented. The various techniques that are considered are: PCA based [7], FMT based [12], SIFT based [3], LBP based [16], SURF based [4], DCT based [19], DCT KPCA based [20], DWT-DCT based [21], SWT-DCT based [22]. The average performance comparison with brightness change, color reduction and blurring operations are illustrated in Fig.…”

“…Proposed method performs well in the presence of this attack (7x7) and achieves TDR of 0.94 and FDR of 0.12. Also, computational complexity of proposed method is compared with other existing methods [3,4,7,12,16,[19][20][21][22]. The computational effort is influenced by the number of overlapping blocks and feature dimension.…”

“…In order to address the problem of rotated or flipped copied portions, Leida Li et al proposed a method [16] [19] concentrated on determining the block size on the detection rate. In [20], Toqeer Mahmood et al proposed a CMF method, explored DCT on overlapping blocks and PCA is employed for dimensionality reduction. Their method detects multiple copy-move forgeries and works well for post-processing attacks.…”