Abstract: Aiming at the problem that the current computer generated image identification algorithm had poor precision in image texture feature identification, the author proposed a computer generated image identification algorithm based on longterm control plan (LTCP) features. Firstly, the color image was transformed into the color model, and the image was sampled to obtain higherscale texture information. Secondly, using the computer generated image blind identification algorithm based on LTCP features and cooccurrence matrix, LTCP features of texture images with different scales and adjacent pixel consistency cooccurrence matrix features were collected. Finally, the LTCP features and the adjacent pixel consistency cooccurrence matrix features were classified and predicted by discriminant classifier, and the computer generated image was identified a
ccording to the classification prediction results. The experimental results show that the proposed algorithm generates images on the computer with low feature dimension, high resolution and accuracy, which can accurately identify computer generated images.

Key words: longterm control plan (LTCP) feature, computer generated image, identification algorithm, color space, down sampling, SVM classifier