Recaptured Images Forensics Based On Color Moments and DCT Coefficients Features

With the development of multimedia technology and digital devices, it is increasingly easier to photograph a high quality image. Due to the facility of capture process, recapture phenomenon becomes popular, which is harmful sometimes. In this paper, an effective recaptured image forensics algorithm through color moments and DCT coefficients features is proposed. Central moments in chromatic space are analyzed to verify the effectiveness in the aspect of detecting recaptured images. The mean, the standard deviation, and the third root of the skewness form the principal features. Furthermore, mode based first digit features of DCT coefficients in both luminance component and chrominance component are presented to distinguish the recaptured images from the realscene images. Finally, these two kinds of features are combined to improve the detection performance. Experimental results demonstrate the proposed method achieves better performance in terms of accuracy.