Abstract: For decades, photographs have often served as evidence in courts. One of the most common forms of photographic manipulation, known as image composition or splicing is analysed in this paper. The goal of blind image forensics is to distinguish original and manipulated images. We propose illumination color as a new indicator for the assessment of image authenticity. Many images exhibit a combination of multiple illuminants (ash photography, mixture of indoor and outdoor lighting, etc.). In the proposed method, the user selects illuminated areas for further investigation. The illuminant colors are locally estimated, effectively decomposing the scene in a map of differently illuminated regions. Inconsistencies in such a map suggest possible image tampering.The information from the physics and statistical-based illuminant estimators on image regions are incorporated to achieve this. From these illuminant estimates, texture and edge-based features are extracted and then provided to a machine-learning approach for decision-making. The classification performance is done by using a Random forest classifier. Automatic face detection is used in order to improve the accuracy of the result.
Keywords: Physics and statistical based illuminant estimator, texture, edge based features, Random forest, and automatic face detection.
[1] Barnard.K, Cardei.C, and Funt.B, "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.
[2] Bianco.S and Schettini.R, "Color constancy using faces,‟in Proc.IEEE Comput. Vision and Pattern Recognition,Providence,‟ RI, USA, Jun. 2012.
[3] Bishop.C.M, "Pattern Recognition and Machine Learning (Information Science and Statistics),‟ Secaucus, NJ,USA: Springer-Verlag New York,2006.
[4] Gijsenij.A, Gevers.T, and van deWeijer.J, "Computational color constancy:Survey and experiments,‟ IEEE Trans. Image Process., vol. 20, no. 9, pp. 2475–2489, Sep. 2011.
[5] Gijsenij.A, Lu.R, and Gevers.T, "Color constancy for multiple light sources,‟ IEEE Trans. Image Process., vol. 21,no. 2, pp. 697–707, Feb. 2012.
[6] Johnson.M and Farid.H, "Exposing digital forgeries by detecting inconsistencies in lighting,‟ in Proc. ACM Workshop on Multimedia and Security, New York, USA,2005, pp. 1–10.
[7] Lukas.J, Fridrich.J, and Goljan.M, "Digital camera identification from sensor pattern noise,‟ IEEE Trans. Inf Forensics Security, vol. 1, no. 2, pp. 205–214, Jun. 2006.
[8] Popescu.A.C and Farid.H, "Statistical tools for digital forensics,‟ in Proc. Inf. Hiding Conf., Jun. 2005, pp. 395–407.
