MENG Xianzhe, NIU Shaozhang, YAN Ru, LI Yezhou. Detecting Photographic Cropping Based on Vanishing Points[J]. Chinese Journal of Electronics, 2013, 22(2): 369-372.
Citation: MENG Xianzhe, NIU Shaozhang, YAN Ru, LI Yezhou. Detecting Photographic Cropping Based on Vanishing Points[J]. Chinese Journal of Electronics, 2013, 22(2): 369-372.

Detecting Photographic Cropping Based on Vanishing Points

Funds:  This work is supported by the National Natural Science Foundation of China (No.61070207).
  • Received Date: 2012-04-01
  • Rev Recd Date: 2012-05-01
  • Publish Date: 2013-04-25
  • Cropping is a common form of manipulation, it is indiscernible and hard to detect, since the interception will not destroy most of the image's original features. In this paper, how to detect cropping according to a single image is described, and a new camera calibration algorithm into digital forensics is proposed, which conducts the calibration according to orthometric vanishing points. Our method can estimate the principal point according to a single image, science the vanishing points only depends on the direction of the object. Experiments show that our method can identify asymmetric cropping of the image effectively, and also can estimate the principal points precisely, besides it is robust to smoothing and noise.
  • loading
  • B. Wang, X. Kong, E. Bertino, H. Fu, "Exposing copy-pasteblur forgeries based on color coherence", Chinese Journal of Electronics, Vol.18, No.3, pp.487-490, 2009.
    Y. Chen and Y. Wang, "Exposing digital forgeries by detecting traces of smoothing", Proc. the 9th International Conference for Young Computer Scientists, pp.1440-1445, 2008.
    F. Huang, J. Huang et al., "Detecting double JPEG compression with the same quantization matrix", IEEE Trans. on Information Forensics and Security, Vol.5, No.4, pp.848-856, 2010.
    E. Kee, H. Farid, "Exposing digital forgeries from 3-D lighting environments", Proc. of Workshop on Information Forensics and Security, Seattle, WA, 2010.
    A. Popescu, H. Farid, "Exposing digital forgeries in color filter array interpolated images", IEEE Trans. Signal Process,Vol.53, No.10, pp.3948-3959, 2005.
    J. Fridrich, M. Goljan, "Identifying images corrected for lens distortion using sensor fingerprints", Proc. SPIE, Electronic Imaging, Media Watermarking, Security, and Forensics XIV, San Francisco, CA, January. pp.-22-26, 2012.
    E. Kee, M. Johnson et al., "Digital image authentication from JPEG headers", IEEE Trans. on Information Forensics and Security, Vol.6, No.3, pp.1066-1075, 2011.
    M. Johnson, H. Farid, "Detecting photographic composites of people", Proc. of 6th International Workshop on Digital Watermarking, Guangzhou, 2007.
    V. Conotter, G. Boato et al., "Detecting photo manipulation on signs and billboards", Proc. ICIP, Hong Kong, 2010.
    Z. Zhang, "A flexible new technique for camera calibration", IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.22, No.11, pp.1330-1334, 2000.
    R. Hartley, A. Zisserman, PHS Torr, D. Davidson, Multiple View Geometry in Computer Vision, Robotica, Cambridge University Press, pp.153-158, 2005.
    F. Liu, R.Wang, "Description of planar line relationship by projective invariant of vanishing points", Acta Electronica Sinica, Vol.29, No.9, pp.1188-1191, 2001. (in Chinese)
    L. Zhang, G. Chen et al., "Cameras calibration based on onedimensional reference object and improved evolutionary strategy", Acta Optica Sinica, Vol.29, No.11, pp.3136-3142, 2009.
    Z. Zhang, "Camera calibration with one-dimensional objects", IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.26, No.7, pp.892-899, 2004.
    H. Gavin, "The Levenberg-Marquardt method for nonlinear least squares curve-fitting problems", Environmental Engineering, pp.1-15, 2010.
    G. Zhang, G. Gong, W. Zhu, "A novel method of color image edge detection based on cloning algorithm", Acta Electronica Sinica, Vol.34, No.4, pp.702-707, 2006. (in Chinese)
  • 加载中

Catalog

    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

    Article Metrics

    Article views (391) PDF downloads(1064) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return