Distinguishing Computer Graphics from Natural Images Based on Statistical Characteristics

Abstract

In this paper, we propose a new discrimination method using image statistical characteristics is proposed which is designed to distinguish natural images from photorealistic computer graphics. Using Benford model as statistical basis, we conclude statistical properties of the MSD (most significant digit) of AC (Alternating Current) coefficients in DCT (Discrete Cosine Transform) domain of natural images and computer graphics, and then we constructed the detection model of the proposed algorithm. Experimental results show that this method can identify natural images and computer graphics effectively, compared with the existing algorithms this method has a higher recognition rate, which comes to 95.22%.