Digital Image Tamper Detection Based on Multimodal Fusion of Residue Features - Advanced Concepts for Intelligent Vision Systems - page 85

intra-frame and inters frame macro blocks, and transforms them into more
discriminatory subspace based on different feature selection techniques. We examined
ICA, CCA and FLD techniques as three different feature selection techniques for two
different image residue features, the noise residue features and quantization residue
features.
Further, we propose a fusion of subspace features and examine the performance of
fusion formulation with three different types of classifier structures: NN classifier,
GMM classifier and SVM classifier. The experimental results show that detection of
tampers in low bandwidth internet video sequences is a challenging task, as traces of
tampering (which leaves traces of periodicity and correlation in macro blocks) can be
damaged by heavy compression used for reducing the bandwidth. However, by using
a pattern recognition and fusion formulation, it is possible to characterise the tamper
and use alternate complementary detector. Further work will focus on examining the
properties of the image at optical level and detecting the perturbations caused by
tampering and extension of propose fusion formulation for development of robust
tamper detection tools.
References
[1] Bayram, S., Sencar, H.T., Memon, N.: An Efficient and Robust Method For Detecting
Copy-Move Forgery. In: Proceedings IEEE International Conference on Acoustics,
Speech and Signal Processing, ICASSP 2009, Taiwan (June 2009)
[2] Dirik, A.E., Memon, N.: Image Tamper Detection Based on Demosaicing Artifacts. In:
Proceedings IEEE ICIP Cairo, Cairo Egypt, November 09 (2009)
[3] Popescu, A.C., Farid, H.: Exposing Digital Forgeries by Detecting Traces of
Re-sampling. IEEE Transactions on signal processing 53(2) (February 2005)
[4] Fridrich J., David, S., Jan, L.: Detection of Copy-Move Forgery in Digital Images,
http://www.ws.binghamton.edu/fridrich/Research/copymove.pdf
[5] Hsu, Y.F., Chang, S.F.: Detecting Image Splicing Using Geometry Invariants and Camera
Characteristics Consistency. In: ICME, Toronto, Canada (July 2006)
[6] Shi, Y.Q., Chen, C., Chen, W.: A natural image model approach to splicing detection. In:
Proc. ACM Multimedia Security Workshop, Dallas, Texas, pp. 51-62 (September 2007)
[7] Gou, H., Swaminathan, A., Wu, M.: Noise Features for Image Tampering Detection and
Steganalysis. In: Proc. of IEEE Int. Conf. On Image Processing (ICIP 2007), San
Antonio, TX (September 2007)
[8] Ng, T.T., Chang, C.S.F., Lin, Y., Sun, Q.: Passive-blind Image Forensics. In: Zeng, W.,
Yu, H., Lin, C.Y. (eds.) Multimedia Security Technologies for Digital Rights. Elsevier,
Amsterdam (2006)
[9] Criminisi, A., Perez, P., Toyama, K.: Region filling and object removal by exemplar-
based image inpainting. IEEE Trans. Image Process. 13(9), 1200-1212 (2004)
[10] Gopi, E.S., Lakshmanan, N., Gokul, T., KumaraGanesh, S., Shah, P.R.: Digital Image
Forgery Detection using Artificial Neural Network and Auto Regressive Coefficients. In:
Proceedings Canadian Conference on Electrical and Computer Engineering, Ottawa,
Canada, May 7-10, pp. 194-197 (2006)
[11] Hsu C., Hung T., Lin C., Hsu C.: Video Forgery Detection Using Correlation of Noise
Residues,
http://www.ee.nthu.edu.tw/~cwlin/pub/mmsp08forensics.pdf
(retrieved on 11/3/2010)