Exposing photo manipulation with inconsistent perspective geometry

doi:10.1016/S1005-8885(14)60320-4

中国邮电高校学报(英文) ›› 2014, Vol. 21 ›› Issue (4): 83-91.doi: 10.1016/S1005-8885(14)60320-4

Exposing photo manipulation with inconsistent perspective geometry

李岩¹,周亚建²,袁开国¹,郭玉翠钮心忻⁴

Information Security Center, Beijing University of Posts and Telecommunications, Beijing 100876, China

收稿日期:2013-12-27 修回日期:2014-05-19 出版日期:2014-08-31 发布日期:2014-08-30
通讯作者: 李岩 E-mail:liyanphoto@gmail.com
基金资助:
新闻出版重大科技工程项目;中央高校基本科研业务费专项资金;中国国家自然科学基金

Exposing photo manipulation with inconsistent perspective geometry

Information Security Center, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2013-12-27 Revised:2014-05-19 Online:2014-08-31 Published:2014-08-30
Contact: Yan LI E-mail:liyanphoto@gmail.com
Supported by:
General Administration of Press and Publication of the People's Republic of China;fundamental research funds for the Central Universities

摘要/Abstract

摘要： Manipulated digital image is got interesting in recent years. Digital images can be manipulated more easily with the aid of powerful image editing software. Forensic techniques for authenticating the integrity of digital images and exposing forgeries are urgently needed. A geometric-based forensic technique which exploits the principle of vanishing points is proposed. By means of edge detection and straight lines extraction, intersection points of the projected parallel lines are computed. The normalized mean value (NMV) and normalized standard deviation (NSD) of the distances between the intersection points are used as evidence for image forensics. The proposed method employs basic rules of linear perspective projection, and makes minimal assumption. The only requirement is that the parallel lines are contained in the image. Unlike other forensic techniques which are based on low-level statistics, this method is less sensitive to image operations that do not alter image content, such as image resampling, color manipulation, and lossy compression. This method is demonstrated with images from York Urban database. It shows that the proposed method has a definite advantage at separating authentic and forged images.

关键词: digital images, forgery detection, image forensics, vanishing points

Abstract: Manipulated digital image is got interesting in recent years. Digital images can be manipulated more easily with the aid of powerful image editing software. Forensic techniques for authenticating the integrity of digital images and exposing forgeries are urgently needed. A geometric-based forensic technique which exploits the principle of vanishing points is proposed. By means of edge detection and straight lines extraction, intersection points of the projected parallel lines are computed. The normalized mean value (NMV) and normalized standard deviation (NSD) of the distances between the intersection points are used as evidence for image forensics. The proposed method employs basic rules of linear perspective projection, and makes minimal assumption. The only requirement is that the parallel lines are contained in the image. Unlike other forensic techniques which are based on low-level statistics, this method is less sensitive to image operations that do not alter image content, such as image resampling, color manipulation, and lossy compression. This method is demonstrated with images from York Urban database. It shows that the proposed method has a definite advantage at separating authentic and forged images.

Key words: digital images, forgery detection, image forensics, vanishing points

中图分类号:

TP391.4

参考文献

1. FARID H. Image forgery detection -- A survey. Signal Processing Magazine, IEEE, 2009, 26(2): 16-25

2. POPESCU A C, FARID H. Exposing digital forgeries by detecting duplicated image regions. Dept Comput Sci, Dartmouth College, Tech Rep TR2004-515, 2004, 11p

3. POPESCU A C, FARID H. Exposing digital forgeries by detecting traces of resampling. Signal Processing, IEEE Transactions on, 2005, 53(2): 758-767

4. LUK Š J, FRIDRICH J. Estimation of primary quantization matrix in double compressed JPEG images. proceedings of the Proc Digital Forensic Research Workshop, F, 2003, 17p

5. PEVNY T, FRIDRICH J. Detection of double-compression in JPEG images for applications in steganography. Information Forensics and Security, IEEE Transactions on, 2008, 3(2): 247-258

6. GLOE T, BOROWKA K, WINKLER A. Efficient estimation and large-scale evaluation of lateral chromatic aberration for digital image forensics. proceedings of the IS&T/SPIE Electronic Imaging, International Society for Optics and Photonics, 2010: 754107/1-13

7. KIRCHNER M. Efficient estimation of CFA pattern configuration in digital camera images. proceedings of the IS&T/SPIE Electronic Imaging, International Society for Optics and Photonics, 2010: 754111/1-12

8. HSU Y-F, CHANG S-F. Image splicing detection using camera response function consistency and automatic segmentation. proceedings of the Multimedia and Expo, IEEE International Conference on, 2007: 28-31

9. LI C T. Source camera identification using enhanced sensor pattern noise. Information Forensics and Security, IEEE Transactions on, 2010, 5(2): 280-287

10. JOHNSON M K, FARID H. Exposing digital forgeries in complex lighting environments. IEEE Transactions on Information Forensics and Security, 2007, 2(3): 450-461

11. KEE E, FARID H. Exposing digital forgeries from 3-D lighting environments. proceedings of the Information Forensics and Security (WIFS), IEEE International Workshop on, 2010: 1-6

12. FARID H, BRAVO M. Image forensic analyses that elude the human visual system. proceedings of the SPIE Symposium on Electronic Imaging, F, 2010: 754106-754106-10

13. O'BRIEN J F, FARID H. Exposing Photo Manipulation with Inconsistent Reflections. ACM Trans Graph, 2012, 31(1): 1-11

14. MENG X Z, NIU S Z, YAN R, et al. Detecting photographic cropping based on vanishing points. Chinese Journal of Electronics, 2013, 22(2): 369-372

15. XU Y, OH S, HOOGS A. A minimum error vanishing point detection approach for uncalibrated monocular images of man-made environments. proceedings of the Computer Vision and Pattern Recognition (CVPR), IEEE Conference on, 2013: 23-28

16. BAZIN J C, YONGDUEK S, DEMONCEAUX C, et al. Globally optimal line clustering and vanishing point estimation in Manhattan world. proceedings of the Computer Vision and Pattern Recognition (CVPR), IEEE Conference on, 2012: 16-21

17. YAO H, WANG S Z, ZHAO Y, et al. Detecting image forgery using perspective constraints. Signal Processing Letters, IEEE, 2012, 19(3): 123-126

18. HARTLEY R, ZISSERMAN A. Multiple view geometry in computer vision. Cambridge Univ Press, 2004

19. CANNY J. A computational approach to edge detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1986, (6): 679-698

20. BALLARD D H. Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognition, 1981, 13(2): 111-122

21. LIEBOWITZ D, ZISSERMAN A. Metric rectification for perspective images of planes. proceedings of the Computer Vision and Pattern Recognition, 1998 Proceedings, IEEE Computer Society Conference on, 1998 :482-488

22. GAVIN H. The Levenberg-Marquardt method for nonlinear least squares curve-fitting problems. Environmental Engineering, 2010: 1-15

23. DENIS P, ELDER J H, ESTRADA F J. Efficient edge-based methods for estimating manhattan frames in urban imagery. Berlin Heidelberg: Springer, 2008: 197-210

[1]	王亮刘贵喜段红岩. Dynamic and combined gestures recognition based on multi-feature fusion in a complex environment [J]. Acta Metallurgica Sinica(English letters), 2015, 22(2): 81-88.
[2]	刘敬徐国胜郑世慧肖达谷利泽. Data streams classification with ensemble model based on decision-feedback[J]. Acta Metallurgica Sinica(English letters), 2014, 21(1): 79-85.
[3]	卢官明左加阔. Orthogonal isometric projection for face recognition[J]. Acta Metallurgica Sinica(English letters), 2011, 18(1): 91-97.

Exposing photo manipulation with inconsistent perspective geometry

Exposing photo manipulation with inconsistent perspective geometry

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价