Entity

Time filter

Source Type


Zhong J.,Guangdong Mechanical and Electrical College | Gan Y.,Guangdong University of foreign Studies
Energy Education Science and Technology Part A: Energy Science and Research | Year: 2014

The recognition of the geometric construction is of great significance in forgery image blind authentication. Geometric moment invariants are highly concentrated image features, with translation, gray, scale, rotation and other global invariance, which is the main method of geometric shape recognition. In recent years, with the development of the digital image forgery blind detection technology, using the moment invariants to extract image features research have gradually become a hot spot, this shows that the moment invariant theory and application in the research of image blind forensics have good prospects for development. This paper mainly introduces and analyzes the concept and features of geometric invariant moments, and their application of image forgery research status, existing problems and future research direction. © Sila Science. All Rights Reserved.


Zhong J.,Guangdong Mechanical and Electrical College | Gan Y.,Guangdong University of foreign Studies
Nonlinear Dynamics | Year: 2015

In recent years, digital image processing has become commonplace with growing powerful and available image editing software. People without any professional technique can also manipulate and forge digital images easily. One of the most popular manners of digital image forgeries is the copy–move image forgery. Extensive researches in detecting copy–move forgery have made a deal of achievements, but most presented methods based on these researches have been only focus on some simple composite forgeries and not able to detect different types of post-processed forgeries. In this paper, we aim to deal with the post-processed forgery operations and scenarios, mainly geometric distortion. We introduce analytical Fourier–Mellin transform (AFMT) and focus on its discretization. We propose discrete analytical Fourier–Mellin transform (DAFMT). We also pay attention to high performance of DAFMT in detecting the copy–move image forgeries. Due to the AFMT described in polar coordinate, so we need to convert coordinate system from polar to Cartesian coordinates. To be computed conveniently, we define an auxiliary disk template to accomplish this conversion. We devote to the use of our proposed DAFMT in detection of image forgeries. A great deal of researches and experiments show that the proposed DAFMT can effectively resist translation, rotation, scaling, and added Gaussian noise operations. Compared with other relevant up-to-date methods, experiments also prove that DAFMT has made a progress in detecting and identifying the forgery images which are suffered from geometric distortion operations. © 2015 Springer Science+Business Media Dordrecht


Zhong J.,Guangdong Mechanical and Electrical College | Gan Y.,Guangdong University of foreign Studies
Journal of Software Engineering | Year: 2015

Copy-move forgery is a common type of image forgery. In the past decades, various types of copy-move forgery image blind authentication approaches have been proposed and these approaches have been used to detect blind forgery images in a number of applications fields. But the robustness of these previously blind authentication approaches against noise and geometric deformation is poor. In this study, the moment invariants which were review are successfully applied in the field of forgery image detection and authentication. Then a new novel approach was proposed for copy-move forgery which is to construct its rotation and scaling moment invariants by using Radon-Bseudo-Fourier-Mellin-Transforms (RBFMT) approach. The experimental results show that the proposed approach can detect copy-move region accurately, even when the copied region was undergone a large angel rotation and scaling tampered. In addition, the robustness of the proposed approach to additive-White Gaussian Noise is greatly improved in comparison with some recent approaches. © 2015 Academic Journals Inc.


Gan Y.,Guangdong University of foreign Studies | Zhong J.,Guangdong Mechanical and Electrical College
Journal of Software Engineering | Year: 2015

Copy-move forgery is one of t he most important types of image tampering. But the algorithms in previous study are less robust to rotation, scaling and additive Gaussian noise. In this study, a new approach was purposed for detecting copy-move forgery in digital images which based on the normalized histogram multi-feature vectors. In order to improve the poor robust in detecting the duplicated image regions, the use of t h e normalized histogram multi-feature vectors of image was proposed to construct feature matrix which is a common component of most proposed copy-move forgery detection schemes. It is proved by experiments that the algorithm can reduce the operand and is provided with the good robust in rotation, scaling and additive Gaussian noise. © 2015 Academic Journals Inc.


Gan Y.,Guangdong University of foreign Studies | Zhong J.,Guangdong Mechanical and Electrical College
Nonlinear Dynamics | Year: 2015

In modern society, as the important medium of information transfer, digital image plays a more and more important role in our daily life. With the modern science and technology revolution, a social phenomenon that people without any professional technique can easily forge and process digital images become commonplace. The image composite forgery, also called copy–move forgery, is the most popular image forged operation. Mostly existing methods are inept for the detection of the composite forgery image underwent geometric distortions. This paper presents a robust and efficient analytical Fourier–Mellin transform (AFMT)-based method. The focus of AFMT method is to construct the scaling and rotation invariant and extract its invariances for the detection of composite forgery. First, the general AFMT expression is given. The radial complex exponential kernel of AFMT is discussed to get the orthogonal feature. Then, the invariant to scaling and rotation is presented to construct the image geometric moment invariants. To extract the scaling and rotation invariance of each pixel of detecting image, a disk template is applied for sliding on the detected image and calculating geometric invariant features. After extracting geometric features, useful geometric features are further filtered from image background information. Then, correlational features of pixels are sorted by lexicographic sorting. Pearson correlation coefficient is applied for identifying the similar continuous regions and locating their positions. Finally, the detected suspicious composite regions are marked. Extensive experiments have been performed to show that the presented AFMT method can detect the composite region in the forgery image precisely. It is also proven that it is more robust and efficient than other existing relevant methods. © 2015 Springer Science+Business Media Dordrecht

Discover hidden collaborations