Forensic identification of compressively sensed images

Xiaoyu Chu, Matthew C. Stamm, W. Sabrina Lin, K. J. Ray Liu
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Due to the ease with which digital images can be forged, a great deal of work has been done in the field of digital image forensics. A particularly important problem is to forensically determine an image's acquisition and storage history. Recent research has shown that a new acquisition technique known as compressive sensing can be used to capture a digital image. Images acquired by compressive sensing can not be easily forensically distinguished from the images captured using standard digital
more » ... g standard digital cameras, nor from those which have undergone Discrete Wavelet Transform (DWT) based compressions. In this paper, we propose a two step detection scheme to identify the images acquired by compressive sensing. The first step identifies unaltered images captured using standard digital cameras and the second step separates compressively sensed images from ones compressed using DWT-based techniques. Our simulations show the first step of detection can achieve a probability of detection (P d ) of 100% for probability of false alarm (P f ) less than 4%, and the second step gets P d nearly 90% with P f of 10%.
doi:10.1109/icassp.2012.6288259 dblp:conf/icassp/ChuSLL12 fatcat:xzxie7hbprg2rmh4lq6dzdaqfy