Nowadays a huge amount of multimedia contents is generated in disparate manners with different devices and then uploaded on the Internet. During upload or once on-line, they are shared with other known users and, ultimately, played or downloaded. These digital assets, accessible on the Internet, mostly flow through social networks (SN) and constitute a real-time source of information. Filter has been performer an image possibly will be of elemental import to go back to its provenance. In this Project it is such a context and proposes an innovative method to inquire if an image derives from a social network. The modus operandi is based on the assumption that each social network applies a peculiar and mostly unknown strategy that however leaves some distinct traces on the image such traces can be extract to feature every dais. By resorting at trained classifiers, the presented methodology is satisfactorily able to discern different social network origin. This method is also able to go back to the original JPEG quality factor the image had before being uploaded on a social network.

Social Network(SN), Multimedia,Classifier,Image Quality

[1].H. Yang and J. Callan, “Near-duplicate detection by instance-level constrained clustering,” inProc. 29th Annu.Int. ACM SIGIR Conf. Res.Develop. Inf. Retr., 2006, pp. 421–428.
[2] M. Henzinger, “Finding near-duplicate Web pages: A large-scale eval-uation of algorithms,” inProc. 29th Annu. Int. ACM SIGIR Conf. Res.Develop. Inf. Retr., 2006, pp. 284–291.
[3] W.-L. Zhao, C.-W.Ngo, H.-K.Tan, and X. Wu, “Near-duplicatekeyframe identification with interest point matching and pattern learning,”IEEE Trans. Multimedia, vol. 9, no. 5, pp. 1037–1048, Aug. 2007.
[4] W.-L. Zhao and C.-W. Ngo, “Scale-rotation invariant pattern entropy forkeypoint-based near-duplicate detection,”
IEEE Trans. Image Process.,vol. 18, no. 2, pp. 412–423, Feb. 2009.
[5] Y. Ke, R. Sukthankar, and L. Huston, “Efficient near-duplicate detectionand sub-image retrieval,” inProc. ACM Multimedia, 2004, pp. 869–876.
[6] L. Kennedy and S.-F. Chang, “Internet image archaeology: Automati-cally tracing the manipulation history of photographs on the Web,” inProc. 16th ACM Int. Conf. Multimedia, 2008, pp. 349–358.
[7] Z. Dias, A. Rocha, and S. Goldenstein, “First steps toward image phy-logeny,” inProc. IEEE Int. Workshop Inf. Forensics Secur., Dec. 2010,pp. 1–6.
[8] Z. Dias, A. Rocha, and S. Goldenstein, “Image phylogeny by minimalspanningtrees,”IEEE Trans. Inf.Forensics Security, vol. 7, no. 2,pp. 774–788, Apr. 2012.
[9] A. De Rosa, F. Uccheddu, A.Costanzo, A.Piva, and M. Barni,“Exploring image dependencies: A new challenge in image forensics,”Proc. SPIE, vol. 7541, p. 75410X, Jan. 2010.
[10] Z. Dias, S. Goldenstein, and A. Rocha, “Toward image phylogenyforests: Automatically recovering semantically similar image relation-ships,”Forensic Sci. Int., vol. 231, nos. 1–3, pp. 178–189, 2013.
[11] F. D. O. Costa, M. A. Oikawa, Z. Dias, S.Goldenstein, andA. R. de Rocha, “Image phylogeny forests reconstruction,”IEEETrans.Inf. Forensics Security, vol. 9, no. 10, pp. 1533–1546, Oct. 2014.
[12] A. Oliveiraet al., “Multiple parenting identification in image phylogeny,”inProc. IEEE Int. Conf. Image Process., Oct. 2014, pp. 5347–5351.
[13] M. A. Fischler and R. C. Bolles, “Random sample consensus: A para-digm for model fitting with applications to image analysisandautomatedcartography,”Commun. ACM, vol. 24, no. 6, pp. 381–395, 1981.
[14] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, “Speeded-up robustfeatures (SURF),”Comput. Vis.Image Understand., vol. 110, no. 3,pp. 346–359, 2008.
[15] J. B. Kruskal, Jr., “On the shortest spanning subtree of a graph andthe traveling salesman problem,”Proc. Amer. Math. Soc., vol. 7, no. 1,pp. 48–50, 1956.
[16] Z. Dias, A.Rocha, and S.Goldenstein, “Exploring heuristic andoptimum branching algorithms for image phylogeny,”J. Vis. Commun.Image Represent., vol. 24, no. 7, pp. 1124–1134, 2013.
[17] R. C. Prim, “Shortest connection networks and some generalizations,”Bell Syst. Tech. J., vol. 36, no. 6, pp. 1389–1401, 1957.
[18] Y. J. Chu and T. H. Liu, “On theshortest arborescence of a directedgraph,”Sci. Sinica, vol. 14, no. 10, pp. 1396–1400, 1965.
[19] J. Edmonds, “Optimum branchings,”J.Res.Nat.Bureau Standards,vol. 71B, no. 4, pp. 233–240, 1967.
[20] F. Bock, “An algorithm to construct a minimum directed spanning treein a directed network,”Develop. Oper. Res., vol. 1, no. 1, pp. 29–44,1971.
[21] I. Amerini, L. Ballan, R. Caldelli, A. Del Bimbo, L. Del Tongo, andG. Serra, “Copy-move forgery detection and localization by means ofrobust clustering with J-Linkage,”Signal Process., Image Commun.,vol. 28, no. 6, pp. 659–669, 2013.
[22] R. Toldo and A. Fusiello, “Robust multiple structures estimation with J-Linkage,” in Proc. 10th Eur. Conf. Comput. Vis., 2008, pp. 537–547.
[23] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,”Int. J. Compute. Vis., vol. 60, no. 2, pp. 91–110, 2004.
[24] F. de O. Costa, A. Oliveira, P. Ferrara, Z. Dias, S. Golden stein, and A. Rocha, “New dissimilarity measures for image phylogeny reconstruction,” Inst. Comput., Univ. Campinas, Campinas, Brazil, Tech. Rep. IC-15-07, Nov. 2015, pp. 1–20.
[25] (2015).figshare. [Online]. Available: http://http://figshare.com/
[26] (2015).Github. [Online]. Available: https://github.com/
[27] P. Pérez, M. Gangnet, and A. Blake, “Poisson image editing,” inProc.ACM Special Interest Group Graph. Interact. Techn., 2003, pp. 313–318.
[28] (2015).Imagemagick. [Online]. Available: http://www.imagemagick.org/script/index.php
[29] H. Jegou, M. Douze, and C. Schmid, “Hamming embedding and weak geometric consistency for large scale image search,” in Proc. Eur. Conf. Comput. Vis., 2008, pp. 304–317.
[30] D. Martin, C. Fowlkes, D. Tal, and J. Malik, “A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics,” in Proc. IEEE Int. Conf. Comput. Vis., vol. 2. Jul. 2001, pp. 416–423