期刊文献+

基于深度学习的图像翻拍检测 被引量:1

Recaptured Image Detection Based on Depth Learning
下载PDF
导出
摘要 随着图像拍摄以及显示技术的发展,图像翻拍质量越来越高,这类图像可能会用作非法途径而不能被认证系统所识别。针对此问题,设计了一种基于深度学习的图像翻拍检测方法,该方法首先分析翻拍图像和真实图像之间的灰度变化,然后将其作为深度信念网络的输入逐层学习抽象的区分特征,最终在网络顶层实现图像的分类。实验结果表明,应用深度学习的方法能正确检测出翻拍图像。 With the development of image capture and display technology, high resolution photos may be used illegal ways because not recognized by the authentication system. Focus on this problem, the method is proposed based on deep learning. This method rooted on gray scale variation between real image and image produced by real image uses gray characteristic as depth belief networks input to learn more abstract feature that can achieve image classification at the top of the network. The experimental results show that the method can correctly detect image produced by real image.
作者 谢心谦 刘霞 孔月萍 XIE Xin-qian, LIU Xia, KONG Yue-ping (School of Information & Control, Xi'an Univ. of Arch. & Tech., Xi'an 710055, China)
出处 《电脑知识与技术》 2017年第6期161-162,177,共3页 Computer Knowledge and Technology
关键词 图像翻拍检测 深度学习 深度信念网络 recaptured image detection deep network deep believe network
  • 相关文献

参考文献5

二级参考文献144

  • 1FARID H. A survey of image forgery detection[ J]. IEEE Signal Processing Magazine, 2009, 26:16 -25.
  • 2CONSTANCE H. Rare-tiger photo flap makes fur fly in China[J]. Science, 2007, 318(5852): 893.
  • 3YU H, NG T T, SUN Q B. Recaptured photo detection using specularity distribution[C]//Proc of IEEE Interna- tional Conference on Image Processing, 2008:3140 - 3143.
  • 4GAO X T, NG T T, QIU B. Single-view recaptured im- age detection based on physics-based features [ C ]//Proc of IEEE International Conference on Multimedia and Ex- po, 2010:1469 -1474.
  • 5CAO H, KOT A. Identification of recaptured photographs on LCD screen[ C ]//Proc of IEEE International Confer- ence on Acoustics, Speech and Signal Processing, 2010: 1790 - 1793.
  • 6CAI S, LI K. Matlab implementation of wavelet trans- forms[EB/OL]. [2010 - 12 - 10]. http://taco, poly. edu/WaveletSoftware/index, html.
  • 7SELESNICK I W. The double-density dual-tree DWT [J]. IEEE Trans. on Signal Processing, 2004,52:1304 -1313.
  • 8LUKAS J, FRIDRICH J. Estimation of primary quantiza- tion matrix in double compressed JPEG images [ C ]//Proc of Digital Forensic Research Workshop, Cleveland, OH, Aug. 2003.
  • 9POPESCU A, Statistical tools for digital image forensics [ D]. Dartmouth College, 2004.
  • 10CHEN C H, SHI Y Q, SU W. A machine learning based scheme for double JPEG compression detection [ C]//Proc of IEEE International Conference on Patten Recognition, 2008 : 1 - 4.

共引文献507

同被引文献5

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部