Copy Move Forgery Image Detection via Discrete Radon and Polar Complex Exponential Transform-Based Moment Invariant Features

Abstract

Copy move forgery with geometric distortions such as the rotational operation, the scaling operation, the mirror operation and the additive noise operation became more common. Existing methods are not competent for the detection of the copy move forgery with these distortions. In fact, the most critical issue for the detection of the forgery is the determination of the geometric features. This paper proposes an efficient Discrete Radon Polar Complex Exponential Transform (DRPCET)-based method for the extraction of the rotational and the scaling invariant features for the copy move forgery detection. First, the features obtained by the Radon transform (RT) and the Polar Complex Exponential Transform (PCET) are fused together. Then, these features are normalized. In order to achieve the scaling invariant property, an auxiliary circular template is introduced. With the auxiliary circular template, the translational moment invariant features, the rotational moment invariant features and the scaling moment invariant features are constructed for the extraction of the planar geometrical features. By further extracting some useful features for the representation of the image background, the interference of the background information can be reduced. After extracting the geometrical features, the lexicographic sorting is applied. Then, a correlation between the same part or similar parts of the image which are copied and moved to another image is computed. Based on the obtained correlations, these forgery parts can be identified and their composed positions can be located. Finally, these images are denoted as the forgery image. Extensive computer numerical simulations have been performed. The obtained results show that the proposed method can detect the copy move region in the forgery image precisely even though the forgery regions are suffered from the mixed geometric distortions.

Colorized Image Forgery Detection based on Similarity Measurement of Gaussian Mixture Distribution

“…Junliu Zhong et al propose an efficient Discrete Radon Polar Complex Exponential Transform (DRPCET)based method for the extraction of the rotational and the scaling invariant features for the copy move forgery detection. The results show that the proposed method can detect the copy move region in the forgery image precisely even though the forgery regions suffered from mixed geometric distortions [12].…”

An efficient novel dual deep network architecture for video forgery detection

“…Table 3 presents the sample forged frame and non-forged frame. DDN model is evaluated considering the accuracy, precision, recall, and F1-score with comparing with various existing model like fast and robust [25], histogram of oriented gradients (HOG) and compression [26], adaptive over segmentation [27], spatio-temporal context [28], inter-frame mechanism [29], local binary patterns (LBP)-detection [30], discrete Radon polar complex exponential transform (DRPCET) [31], fast and effective [32], and existing model i.e. video forgery detection using the histogram of second order gradients (VFDHSOG) [33].…”

A Duplicated Forgery Detection Fusion Algorithm using SIFT and Radial-Harmonic Fourier Moments

“…There are several types of forgeries. One of the most common type is duplicated forgery or so-called copy-move forgery [23]. In this type, a part of the image is copied and moved to another part of the image that aims to cover some object by one's intention.…”