ABSTRACT
The sensor pattern noise (SPN) based source camera identification technique has been well established. The common practice is to subtract a denoised image from the original one to get an estimate of the SPN. Various techniques to improve SPN's reliability have previously been proposed. Identifying the most effective technique is important, for both researchers and forensic investigators in law enforcement agencies. Unfortunately, the results from previous studies have proven to be irreproducible and incomparable dash there is no consensus on which technique works the best. Here, we extensively evaluate various ways of enhancing the SPN by using the public Dresden database. We identify which enhancing methods are more effective and offer some insights into the behavior of SPN. For example, we find that the most effective enhancing methods share a common strategy of spectrum flattening. We also show that methods that only aim at reducing the contamination from image content do not lead to satisfying results, since the non-unique artifacts (NUA) among different cameras are the major troublemaker to the identification performance. While there is a trend of employing sophisticate methods to predict the impact of image content, our results suggest that more effort should be invested to tame the NUAs.
- I. Amerini, R. Caldelli, V. Cappellini, F. Picchioni, and A. Piva. Analysis of denoising filters for photo response non uniformity noise extraction in source camera identification. In Digital Signal Processing, 2009 16th International Conference on, pages 1--7. IEEE, 2009. Google ScholarDigital Library
- L.-H. Chan, N.-F. Law, and W.-C. Siu. A confidence map and pixel-based weighted correlation for prnu-based camera identification. Digital Investigation, 10(3):215--225, 2013. Google ScholarDigital Library
- M. Chen, J.Fridrich, M.Goljan, and J.Lukas. Determining image origin and integrity using sensor noise. IEEE Trans.Inf.Forensics Security, 3(1):74 -- 90, 2008. Google ScholarDigital Library
- G. Chierchia, S. Parrilli, G. Poggi, C. Sansone, and L. Verdoliva. On the influence of denoising in prnu based forgery detection. In Proceedings of the 2nd ACM workshop on Multimedia in forensics, security and intelligence, pages 117--122. ACM, 2010. Google ScholarDigital Library
- A. Cortiana, V. Conotter, G. Boato, and F. G. De Natale. Performance comparison of denoising filters for source camera identification. In IS&T/SPIE Electronic Imaging, pages 788007--788007. International Society for Optics and Photonics, 2011.Google Scholar
- T. Gloe and R. Böhme. The dresden image database for benchmarking digital image forensics. Journal of Digital Forensic Practice, 3(2--4):150--159, 2010.Google ScholarCross Ref
- T. Gloe, S. Pfennig, and M. Kirchner. Unexpected artefacts in prnu-based camera identification: a dresden image database case-study. In Proceedings of the on Multimedia and security, pages 109--114. ACM, 2012. Google ScholarDigital Library
- M. Goljan and J. Fridrich. Camera identification from cropped and scaled images. In Electronic Imaging 2008, pages 68190E--68190E. International Society for Optics and Photonics, 2008.Google Scholar
- J.Lukas, J.Fridrich, and M.Goljan. Digital camera identification from sensor pattern noise. IEEE Trans.Inf.Forensics Security, 1(2):205 -- 214, 2006. Google ScholarDigital Library
- X. Kang, Y. Li, Z. Qu, and J. Huang. Enhancing roc performance of trustworthy camera source identification. In IS&T/SPIE Electronic Imaging, pages 788009--788009, 2011.Google Scholar
- X. Kang, Y. Li, Z. Qu, and J. Huang. Enhancing source camera identification performance with a camera reference phase sensor pattern noise. IEEE Trans.Inf.Forensics Security, 7(2):393 -- 402, 2012. Google ScholarDigital Library
- C.-T. Li. Source camera identification using enhanced sensor pattern noise. IEEE Trans.Inf.Forensics Security, 5(2):280 -- 287, 2010. Google ScholarDigital Library
- S. McCloskey. Confidence weighting for sensor fingerprinting. In Computer Vision and Pattern Recognition Workshops, 2008. CVPRW'08. IEEE Computer Society Conference on, pages 1--6, 2008.Google ScholarCross Ref
- M. Mihcak, I. Kozintsev, and K. Ramchandran. Spatially adaptive statistical modeling of wavelet image coefficients and its application to denoising. In Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on, volume 6, pages 3253--3256, 1999. Google ScholarDigital Library
- W. van Houten and Z. Geradts. Using anisotropic diffusion for efficient extraction of sensor noise in camera identification. Journal of forensic sciences, 57(2):521--527, 2012.Google Scholar
Index Terms
- Enhancing Sensor Pattern Noise for Source Camera Identification: An Empirical Evaluation
Recommendations
Building fingerprints with information from three color bands for source camera identification
MiFor '10: Proceedings of the 2nd ACM workshop on Multimedia in forensics, security and intelligenceThe imaging sensor (e.g., CCD, CMOS) pattern noise is a noise-like spread-spectrum signal that mainly consists of the photo-response non-uniformity (PRNU) noise. Since each camera has a unique PRNU, the PRNU becomes a popular fingerprint for source ...
An Effective Training Strategy for Enhanced Source Camera Device Identification
Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and ChallengesAbstractSource camera identification is a forensic problem of linking an image in question to the camera used to capture it. This could be a useful tool in forensic applications to identify potential suspects of cybercrime. Over the last decade, several ...
Source Camera Device Identification from Videos
AbstractSource camera identification is an important and challenging problem in digital image forensics. The clues of the device used to capture the digital media are very useful for Law Enforcement Agencies (LEAs), especially to help them collect more ...
Comments