Automatic Machine Learning Forgery Detection Based On Svm Classifier

International Journal of Mechanical Engineering

© 2014 by SSRG - IJME Journal

Volume 1 Issue 1

Year of Publication : 2014

Authors : S.L.Jothilakshmi, K Valli, A.Vanitha, A. Selva nathiya, A.Shunmuga priya

10.14445/23488360/IJME-V1I1P101

How to Cite?

S.L.Jothilakshmi, K Valli, A.Vanitha, A. Selva nathiya, A.Shunmuga priya, "Automatic Machine Learning Forgery Detection Based On Svm Classifier," SSRG International Journal of Mechanical Engineering, vol. 1,  no. 1, pp. 1-5, 2014. Crossref, https://doi.org/10.14445/23488360/IJME-V1I1P101

Abstract:

Photographers are able to create composites of analog pictures, this process  is  very time  consuming  and  require  expert  knowledge.  In digital image the editing software makes modifications in  straight forward.  In  this  project  analyze  one  of  the  most common  form  of photographic   manipulation   known   as   image   composition   or splicing.For  that  propose  a  forgery  detection  method  is  used  to exploits  subtle  inconsistencies  in  the  colour  of  the  illumination  of images.   The   technique   ( Machine   Learning)   is   applicable   to images containing two or more people. To achieving this concept, the    information    from    physics    (chromaticity)- and   statistical (texture and  edge) - based  illuminate  estimators on  image  regions of  similar  images  are  taken.  Then  the  extracted  texture,  skin pigmentation - and edge - based features are provided to a machine - learning approach for automatic decision - making. The classification performance achieved by an SVM (Support Vector Machine) meta - fusion classifier.

Keywords:

Color constancy, illuminant color, image forensics, machine   learning,   spliced   image   detection,   texture   and   edge descriptors.

References:

[1]A.Rocha,W.Scheirer,T.E.Boult,andS.Goldenstein,“Vision of the unseen: Current trends and challenges in digital image and video
forensics,” ACM Comput. Surveys, vol. 43, pp. 1–42, 2011.
[2] C. Riess and E. Angelopoulou, “Scene illumination as an indicator of image manipulation,” Inf. Hiding , vol. 6387, pp. 66–80, 2010.
[3] H. Farid and M. J. Bravo, “Image forensic analyses that elude the human visual system,” inProc. Symp. Electron. Imaging (SPIE), 2010, pp. 1–10
[4] Y. Ostrovsky, P. Cavanagh, and P. Sinha, “Perceiving illumination in-consistencies in scenes,”Perception, vol. 34, no. 11, pp. 1301–1314, 2005.
[5] H. Farid, A 3-D lighting and shadow analysis of the JFK Zapruder fi lm (Frame 317), Dartmouth College, Tech. Rep. TR2010–677, 2010.
[6] M. Johnson and H. Farid, “Exposing digital forgeries by detecting in-consistencies in lighting,” in Proc. ACM Workshop on Multimedia and Security, New York, NY, USA, 2005, pp. 1–10.
[7]M.JohnsonandH.Farid,“Exposing digital forgeries in complex
lighting environments,” IEEE Trans. Inf. Forensics Security ,vol.3,
no. 2, pp. 450–461, Jun. 2007.
[8] M. Johnson and H. Farid, “Exposing digital forgeries through specular highlights on the eye,” in Proc. Int. Workshop on Inform. Hiding, 2007,pp. 311–325.
[9] E. Kee and H. Farid, “Exposing digital forgeries from 3-D lighting en-vironments,” in Proc. IEEE Int. Workshop on Inform. Forensics and
Security (WIFS) , Dec. 2010, pp. 1–6.
[10] W. Fan, K. Wang, F. Cayre, and Z. Xiong, “3D lighting-based image forgery detection using shape-from-shading,” in Proc. Eur. Signal Pro-cessing Conf. (EUSIPCO) , Aug. 2012, pp. 1777–1781.
[11] J. F. O’Brien and H. Farid, “Exposing photo manipulation with incon-sistent re fl ections,” ACM Trans. Graphics , vol. 31, no. 1, pp. 1–11, Jan.2012.
[12] S. Gholap and P. K. Bora, “Illuminant colour based image forensics,” in Proc. IEEE Region 10 Conf., 2008, pp. 1–5.
[13] X. Wu and Z. Fang, “Image splicing detection using illuminant color in-consistency,” in Proc. IEEE Int. Conf. Multimedia Inform. Networking and Security, Nov. 2011, pp. 600–603.
[14] P. Saboia, T. Carvalho, and A. Rocha, “Eye specular highlights telltales for digital forensics: A mach ine learning ap proach,” in Proc. IEEE Int. Conf. Image Processing (ICIP), 2011, pp. 1937–1940.
[15] C. Riess and E. Angelopoulou, “Physics-based illuminant color esti-mation as an image semantics clue,” inProc. IEEE Int. Conf. Image Processing, Nov. 2009, pp. 689–692.
[16] K. Barnard, V. Cardei, and B. Funt, “A comparison of computational color constancy algorithms–Part I: Methodology and Experiments With Synthesized Data,”IEEE Trans. Image Process. ,vol.11,no.9, pp. 972–983, Sep. 2002.
[17]K.Barnard,L.Martin,A.Coath,andB.Funt,“Acomparisonof
computational color constancy algorithms – Part II: Experiments With Image Data,” IEEE Trans. Image Process., vol. 11, no. 9, pp. 985–996, Sep. 2002.