Beijing Chen, Ye Gao, Lingzheng Xu, Xiaopeng Hong, Yuhui Zheng, Yun-Qing Shi. Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field. Mathematical Biosciences and Engineering, 2019, 16(6): 6907-6922. doi: 10.3934/mbe.2019346
Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field
|Author:||Chen, Beijing1,2,3; Gao, Ye1; Xu, Lingzheng4;|
1Jiangsu Engineering Center of Network Monitoring, School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing 210044, China
2Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science & Technology, Nanjing 210044, China
3Key Laboratory of Computer Network Technology of Jiangsu Province, Southeast University, Nanjing 210096, China
4College of Computer Science, Sichuan University, Chengdu 610065, China
5Center for Machine Vision and Signal Analysis, University of Oulu, Oulu FI-90014, Finland
6Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark 07102, USA
|Online Access:||PDF Full Text (PDF, 0.9 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe202002286804
American Institute of Mathematical Sciences,
|Publish Date:|| 2020-02-28
Recently, fully convolutional network (FCN) has been successfully used to locate spliced regions in synthesized images. However, all the existing FCN-based algorithms use real-valued FCN to process each channel separately. As a consequence, they fail to capture the inherent correlation between color channels and the integrity of three channels. So, in this paper, quaternion fully convolutional network (QFCN) is proposed to generalize FCN to quaternion domain by replacing real-valued conventional blocks in FCN with quaternion conventional blocks. In addition, a new color image splicing localization algorithm is proposed by combining QFCNs and superpixel (SP)-enhanced pairwise conditional random field (CRF). QFCNs consider three different versions (QFCN32, QFCN16, and QFCN8) with different up-sampling layers. The SP-enhanced pairwise CRF is used to refine the results of QFCNs. Experimental results on three publicly available datasets demonstrate that the proposed algorithm outperforms the existing algorithms including some conventional algorithms and some deep learning-based algorithms.
Mathematical biosciences and engineering
|Pages:||6907 - 6922|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
This work was supported in part by NSFC under Grants 61572258, 61771231, 61772281, and 61672294, in part by the PAPD fund, and in part by Qing Lan Project.
© 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0).