Source Camera Identification Based on In-and-Inter Channel Traces
Yong Jie Xie, Yi Bao, Sen Feng Tong, Yu Hao Yang · Applied Mechanics and Materials · 2013
Source camera detecting, which is about establishing whether or not the images of interest are taken by the same camera, is a challenging problem. Most CFA(color filter array) interpolation algorithm characterize the feature of camera which take the image. In this paper, we propose an improved algorithm. Instead of using inter-channel demosaicking/color interpolation traces, we first extract four in-and-inter-channel variance maps, respectively, and then extract the shape, similarity and difference features of maps for camera model identification. The experimental results show that the method had significantly improved the accuracy rate of source digital image identification.