Open Access
ARTICLE
Resampling Factor Estimation via Dual-Stream Convolutional Neural Network
1 School of Data and Computer Science, Guangdong Province Key Laboratory of Information Security Technology, Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing, Sun Yat-sen University, Guangzhou, 510006, China
2 Academy of Forensic Science, Shanghai, 200063, China
3 College of Information Science and Technology, Jinan University, Guangzhou, 510632, China
4 Department of Computer Science, University of Massachusetts Lowell, Lowell, MA 01854, USA
* Corresponding Author: Wei Lu. Email:
Computers, Materials & Continua 2021, 66(1), 647-657. https://doi.org/10.32604/cmc.2020.012869
Received 15 July 2020; Accepted 28 August 2020; Issue published 30 October 2020
Abstract
The estimation of image resampling factors is an important problem in image forensics. Among all the resampling factor estimation methods, spectrumbased methods are one of the most widely used methods and have attracted a lot of research interest. However, because of inherent ambiguity, spectrum-based methods fail to discriminate upscale and downscale operations without any prior information. In general, the application of resampling leaves detectable traces in both spatial domain and frequency domain of a resampled image. Firstly, the resampling process will introduce correlations between neighboring pixels. In this case, a set of periodic pixels that are correlated to their neighbors can be found in a resampled image. Secondly, the resampled image has distinct and strong peaks on spectrum while the spectrum of original image has no clear peaks. Hence, in this paper, we propose a dual-stream convolutional neural network for image resampling factors estimation. One of the two streams is gray stream whose purpose is to extract resampling traces features directly from the rescaled images. The other is frequency stream that discovers the differences of spectrum between rescaled and original images. The features from two streams are then fused to construct a feature representation including the resampling traces left in spatial and frequency domain, which is later fed into softmax layer for resampling factor estimation. Experimental results show that the proposed method is effective on resampling factor estimation and outperforms some CNN-based methods.Keywords
Cite This Article
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.