Identifying Device Brand by Using Characteristics of Color Filter Array

In this paper, we propose a passive scheme for photorealistic com-puter generated image (PRCG) identification and device brand classification. To this end, a periodic phenomenon of variance of pixel values resulting from demosaicing process is analyzed in RGB color space. Based on the phenome-non, the proposed scheme is composed of color space transformation, high-pass filtering, feature extraction, and classification. To make the phenomenon ob-vious, a high-pass filter is performed. The periodic phenomenons in different directions are measured as features in the Fourier domain and combined with a hierarchical classifier for PRCG detection and brand identification simulta-neously. Experimental results show that our proposed scheme can not only detect photographic images (PIM) but also determine what brand of a camera is used.