期刊名称：International Journal of Hybrid Information Technology
印刷版ISSN：1738-9968
出版年度：2010
卷号：3
期号：1
出版社：SERSC
摘要：The identification of source camera is useful to improve the capability of evidence in the digital image such as distinguish the photographer taking illegal images and adopting digital images as evidence of crime. Lukáš, et al. showed the method for source camera identification based on the correlation of PNU (pixel non-uniformity) noise. However, the wavelet-based denoising filter for suppressing the random noise reduces the accuracy of camera identification. It is caused by the fact that the denoising filter diffuses the edge and makes the PNU noise less pronounced. Moreover, it is difficult to extract PNU noise from the images taken by cameras which are equipped with the image improvement functions such as motion blur correction, contrast enhancement, and noise reduction. In this paper, we propose a method for improving the camera identification accuracy by selecting pixels based on the texture complexity. We also propose a method for improving the identification accuracy by applying the image restoration method
关键词：PNU Noise; Camera Identification; Image Restoration
