Resampling parameter estimation via dual-filtering based convolutional neural network
- PDF / 802,233 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 77 Downloads / 187 Views
SPECIAL ISSUE PAPER
Resampling parameter estimation via dual‑filtering based convolutional neural network Lin Peng1 · Xin Liao1,2 · Mingliang Chen3 Received: 1 July 2020 / Accepted: 20 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Resampling detection is an important problem in image forensics. Several exiting approaches have been proposed to solve it, but few of them focus on resampling parameter estimation. Especially, the estimation of downsampling scenarios is very challenging. In this paper, we propose a dual-filtering based convolutional neural network (CNN) to extract features directly from the images. First, we analyze the formulation of resampling parameter estimation and reformulate it as a multi-classification problem by regarding each resampling parameter as a distinct class. Then, we design a network structure based on the preprocessing operation to capture the specific resampling traces for classification. Two parallel filters with different highpass filters are deployed to the CNN architecture, which enlarges the resampling traces and makes it easier to achieve resampling parameter estimation. Next, concatenating the outputs of the two filters by a “concat” layer. Finally, the experimental results demonstrate our proposed method is effective and has better performance than state-of-the-art methods in resampling parameter estimation. Keywords Image forensics · Resampling detection · Parameter estimation · Convolutional neural network · Dual-filtering
1 Introduction Digital images play an important role in disseminating information, but it is very easy to manipulate images due to powerful image processing software. Currently, the authenticity of digital images has been doubtful. In reality, there are various methods of image tampering, such as rotation, scaling, clipping, synthesis and JPEG compression. Therefore, image forgery detection is significant and digital image forensics technology has become a meaningful research topic [1, 2]. In recent years, several remarkable works in image forensics have been reported for detecting different tampering operations, such as copy-move detection [3], splicing detection [4], median filtering detection [5], resampling detection * Xin Liao [email protected] 1
College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China
2
State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Science, Beijing 100093, China
3
Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, USA
[6] and operator chain detection [7]. Generally speaking, specific tampering traces are corresponding to different tampering operations. Thus, the majority of tampering detection approaches are based on inherent statistical characteristics. These contributions made in image forensics protect the authenticity and integrity of images. Resampling is a common image processing manipulation in daily life, which is mainly use
Data Loading...
