Research article Special Issues

Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field

  • Received: 04 March 2019 Accepted: 22 July 2019 Published: 29 July 2019
  • 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.

    Citation: 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[J]. Mathematical Biosciences and Engineering, 2019, 16(6): 6907-6922. doi: 10.3934/mbe.2019346

    Related Papers:

  • 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.


    加载中


    [1] G. K. Birajdar and V. H. Mankar, Digital image forgery detection using passive techniques: A survey, Digit. Invest., 10(2013), 226–245.
    [2] B. J. Chen, M. Yu, Q. T. Su, et al., Fractional quaternion cosine transform and its application in color image copy-move forgery detection, Multimed. Tools Appl., (2018), 1–17.
    [3] C. M. Pun, B. Liu and X. C. Yuan, Multi-scale noise estimation for image splicing forgery detection, J. Vis. Commun. Image Represent., 10(2016), 195–206.
    [4] B. Mahdian and S. Saic, Using noise inconsistencies for blind image forensics, Image Vis. Comput., 27(2009), 1497–1503.
    [5] S. Lyu, X. Pan and X. Zhang, Exposing region splicing forgeries with blind local noise estimation, Int. J. Comput. Vis., 110(2014), 202–221.
    [6] P. Ferrara, T. Bianchi, R. A. De, et al., Image forgery localization via fine-grained analysis of CFA artifacts, IEEE Trans. Inf. Forensic Secur., 10(2013), 226–245.
    [7] A. E. Dirik and N. Memon, Image tamper detection based on demosaicing artifacts, In: IEEE International Conference on Image Processing, (2009), 1497–1500.
    [8] E. González, A. Sandoval, L. García, et al., Digital image tamper detection technique based on spectrum analysis of CFA artifacts, Sensors, 18(2018), 2804.
    [9] Z. Lin, J. He, X. Tang, et al., Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis, Pattern Recognit., 42(2009), 2492–2501.
    [10] T. Bianchi and A. Piva, Image forgery localization via block-grained analysis of JPEG artifacts, IEEE Trans. Inf. Forensic Secur., 7(2012), 1003–1017.
    [11] S. M. Ye, Q. Sun and E. C. Chang, Detecting digital image forgeries by measuring inconsistencies of blocking artifact, In: IEEE International Conference on Multimedia and Expo, (2007), 12–15.
    [12] W. Li, Y. Yuan and N. Yu, Passive detection of doctored JPEG image via block artifact grid extraction, Signal Process., 89(2009), 1821–1829.
    [13] W. Luo, J. Huang and G. Qiu, JPEG error analysis and its applications to digital image forensics, IEEE Trans. Inf. Forensic Secur., 5(2010), 480–491.
    [14] F. Huang, J. Huang and Y. Q. Shi, Detecting double JPEG compression with the same quantization matrix, IEEE Trans. Inf. Forensic Secur., 5(2010), 848–856.
    [15] A. C. Popescu and H. Farid, Exposing digital forgeries by detecting traces of resampling, IEEE Trans. Signal Process., 53(2005), 758–767.
    [16] H. D. Li, W. Q. Luo, X. Q. Qiu, et al., Image forgery localization via integrating tampering possibility maps, IEEE Trans. Inf. Forensic Secur., 12(2017), 1240–1252.
    [17] D. Cozzolino, G. Poggi and L. Verdoliva, Recasting residual-based local descriptors as convolutional neural networks: an application to image forgery detection, In: ACM Workshop on Information Hiding and Multimedia Security, (2017), 159–164.
    [18] Y. Liu, Q. Guan, X. Zhao, et al., Image forgery localization based on multi-scale convolutional neural networks, In: ACM Workshop on Information Hiding and Multimedia Security, (2018), 85–90.
    [19] J. H. Bappy, A. K. Roy, J. Bunk, et al., Exploiting spatial structure for localizing manipulated image regions, In: IEEE International Conference on Computer Vision, (2017), 4970–4979.
    [20] Z. Shi, X. Shen and H. Kang, Image manipulation detection and localization based on the dual-domain convolutional veural networks, IEEE Access, 6(2018), 76437–76453.
    [21] R. Salloum, Y. Ren and C. C. J. Kuo, Image splicing localization using a multi-task gully convolutional network (MFCN), J. Vis. Commun. Image Represent., 51(2018), 201–209.
    [22] B. Liu and C. M. Pun, Locating splicing forgery by fully convolutional networks and conditional random field, Signal Process.Image Commun., 66(2018), 103–112.
    [23] B. J. Chen, X. M. Qi, Y. T. Wang, et al., An Improved Splicing Localization Method by Fully Convolutional Networks, IEEE Access, 6(2018), 69472–69480.
    [24] J. H. Bappy, C. Simons, L. Nataraj, et al., Hybrid LSTM and encoder-decoder architecture for detection of image forgeries, IEEE Trans. Image Process., 28(2019), 3286–3300.
    [25] T. Parcollet, M. Morchid and G. Linarès, Quaternion convolutional neural networks heterogeneous image processing, preprint, arXiv: 1811.02656.
    [26] T. A. Ell and S. J. Sangwine, Hypercomplex fourier transforms of color images, IEEE Trans. Image Process., 16(2007), 22–35.
    [27] B. J. Chen, G. Coatrieux, G. Chen, et al., Full 4-D quaternion discrete Fourier transform based watermarking for color images, Digit. Signal Proc., 28(2014), 106–119.
    [28] N. Matsui, T. Isokawa, H. Kusamichi, et al., Quaternion neural network with geometrical operators, J. Intell. Fuzzy Syst., 15(2004), 149–164.
    [29] X. Xu, Z. Guo, C. Song, et al., Multispectral palmprint recognition using a quaternion matrix, Sensors, 12(2012), 4633–4647.
    [30] B. J. Chen, J. H. Yang, B. Jeon, et al., Kernel quaternion principal component analysis and its application in RGB-D object recognition, Neurocomputing, 266(2017), 293–303.
    [31] G. L. Xu, X. T. Wang and X. G. Xu, Fractional quaternion Fourier transform, convolution and correlation, Signal Process., 88(2008), 2511–2517.
    [32] B. J. Chen, C. F. Zhou, B. Jeon, et al., Quaternion discrete fractional random transform for color image adaptive watermarking, Multimed. Tools Appl., 77(2018), 20809–20837.
    [33] K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition, preprint, arXiv: 1409.1556.
    [34] Q. Cui, S. McIntosh and H. Y. Sun, Identifying materials of photographic images and photorealistic computer generated graphics based on deep CNNs, Comput. Mat. Contin., 55(2018), 229–241.
    [35] H. Y. Zhao, C. Che, B. Jin, et al., A viral protein identifying framework based on temporal convolutional network, Math. Biosci. Eng., 16(2019), 1709–1717.
    [36] L. G. Zheng and C. Song, Fast near-duplicate image detection in Riemannian space by a novel hashing scheme, Comput. Mat. Contin., 56(2018), 529–539.
    [37] K. He, X. Zhang, S. Ren, et al., Deep residual learning for image recognition, In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), (2016), 770–778.
    [38] X. Zhu, Y. Xu and H. Xu, Quaternion convolutional neural networks, In: European Conference on Computer Vision, (2018), 631–647.
    [39] C. J. Gaudet and A. S. Maida, Deep quaternion networks, In: IEEE International Joint Conference on Neural Networks, (2018), 1–8.
    [40] S. Ioffe and C. Szegedy, Batch normalization: accelerating deep network training by reducing internal covariate shift, In: International Conference on International Conference on Machine Learning, (2015), 448–456.
    [41] E. Shelhamer, J. Long and T. Darrell, Fully Convolutional Networks for Semantic Segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 39(2014), 640–651.
    [42] A. Arnab, S. Jayasumana, S. Zheng, et al., Higher order conditional random fields in deep neural networks, In: European Conference on Computer Vision, (2016), 524–540.
    [43] Y. H. Zheng, L. Sun, S. F. Wang, et al., Spatially regularized structural support vector machine for robust visual tracking. IEEE Trans. Neural Netw. Learn. Syst., 2018. DOI: 10.1109/tnnls.2018.2855686
    [44] L. Sulimowicz, I. Ahmad and A. Aved, Superpixel-enhanced pairwise conditional random field for semantic segmentation, In: IEEE International Conference on Image Processing, (2018), 271–275.
    [45] P. Kohli and P. H. S. Torr, Robust higher order potentials for enforcing label consistency, Int. J. Comput. Vis., 82(2009), 302–324.
    [46] J. Dong and W. Wang, CASIA tampered image detection evaluation (TIDE) database, v1.0 and v2.0, Chinese Academy of Sciences, 2011, Available online: http://forensics.idealtest.org/.
    [47] T. T. Ng and S. F. Chang, A dataset of authentic and spliced image blocks, Columbia University, 2004, Available online: http://www.ee.columbia.edu/ln/dvmm/downloads/.
    [48] M. Zampoglou, S. Papadopoulos and Y. Kompatsiaris, Large-scale evaluation of splicing localization algorithms for web images, Multimed. Tools Appl., 76(2017), 1–34.
    [49] F. Xiao, L.Chen, H. Zhu, et al., Anomaly-tolerant network traffic map estimation via noise-immune temporal matrix completion, IEEE J. Sel. Area. Comm., 37(2019), 1192–1204.
  • Reader Comments
  • © 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)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(3350) PDF downloads(519) Cited by(5)

Article outline

Figures and Tables

Figures(7)  /  Tables(2)

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog