Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2019-07-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/10.3934/mbe.2019346?viewType=HTML |
| _version_ | 1828365375047204864 |
|---|---|
| author | Beijing Chen Ye Gao Lingzheng Xu Xiaopeng Hong Yuhui Zheng Yun-Qing Shi |
| author_facet | Beijing Chen Ye Gao Lingzheng Xu Xiaopeng Hong Yuhui Zheng Yun-Qing Shi |
| author_sort | Beijing Chen |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-14T05:30:18Z |
| format | Article |
| id | doaj.art-8cee9dedf1fa4b538bc10ddc2535cd02 |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-14T05:30:18Z |
| publishDate | 2019-07-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-8cee9dedf1fa4b538bc10ddc2535cd022022-12-22T02:09:49ZengAIMS PressMathematical Biosciences and Engineering1551-00182019-07-011666907692210.3934/mbe.2019346Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random fieldBeijing Chen0Ye Gao1Lingzheng Xu2Xiaopeng Hong3Yuhui Zheng4Yun-Qing Shi 51. Jiangsu Engineering Center of Network Monitoring, School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing 210044, China 2. Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science & Technology, Nanjing 210044, China 3. Key Laboratory of Computer Network Technology of Jiangsu Province, Southeast University, Nanjing 210096, China1. Jiangsu Engineering Center of Network Monitoring, School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing 210044, China4. College of Computer Science, Sichuan University, Chengdu 610065, China5. Center for Machine Vision and Signal Analysis, University of Oulu, Oulu FI-90014, Finland1. Jiangsu Engineering Center of Network Monitoring, School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing 210044, China 2. Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science & Technology, Nanjing 210044, China1. Jiangsu Engineering Center of Network Monitoring, School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing 210044, China6. Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark 07102, USARecently, 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.https://www.aimspress.com/article/10.3934/mbe.2019346?viewType=HTMLsplicing localizationsplicing detectionquaternionfully convolutional networkconditional random field |
| spellingShingle | 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 splicing localization splicing detection quaternion fully convolutional network conditional random field |
| title | Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field |
| title_full | Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field |
| title_fullStr | Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field |
| title_full_unstemmed | Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field |
| title_short | Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field |
| title_sort | color image splicing localization algorithm by quaternion fully convolutional networks and superpixel enhanced pairwise conditional random field |
| topic | splicing localization splicing detection quaternion fully convolutional network conditional random field |
| url | https://www.aimspress.com/article/10.3934/mbe.2019346?viewType=HTML |
| work_keys_str_mv | AT beijingchen colorimagesplicinglocalizationalgorithmbyquaternionfullyconvolutionalnetworksandsuperpixelenhancedpairwiseconditionalrandomfield AT yegao colorimagesplicinglocalizationalgorithmbyquaternionfullyconvolutionalnetworksandsuperpixelenhancedpairwiseconditionalrandomfield AT lingzhengxu colorimagesplicinglocalizationalgorithmbyquaternionfullyconvolutionalnetworksandsuperpixelenhancedpairwiseconditionalrandomfield AT xiaopenghong colorimagesplicinglocalizationalgorithmbyquaternionfullyconvolutionalnetworksandsuperpixelenhancedpairwiseconditionalrandomfield AT yuhuizheng colorimagesplicinglocalizationalgorithmbyquaternionfullyconvolutionalnetworksandsuperpixelenhancedpairwiseconditionalrandomfield AT yunqingshi colorimagesplicinglocalizationalgorithmbyquaternionfullyconvolutionalnetworksandsuperpixelenhancedpairwiseconditionalrandomfield |