Title: Identifying natural images and computer-generated graphics based on convolutional neural network

Authors: Min Long; Sai Long; Fei Peng; Xiao-hua Hu

Addresses: School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, Hunan, 410114, China ' School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, Hunan, 410114, China ' School of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, 410082, China ' School of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, 410082, China

Abstract: Aiming at the identification of natural images and computer-generated graphics, an image source pipeline forensics method based on convolutional neural network (CNN) is proposed. In this method, Inception-v3 is used as the basic network, and the pre-trained model parameters in ImageNet are adopted. The top-level classification layer of Inception-v3 is replaced by two fully-connected Softmax classifiers. With the transfer learning, a new network model is constructed. The network is fine-tuned by a database with 10,000 images to identify natural images and computer-generated graphics. Experimental results and analysis show that it can effectively identify natural images and computer-generated graphics, and it is robustness against JPEG compression, scaling, rotation, noise and other post-processing operations. Furthermore, the effect of Softmax classifier and SVM classifier on the experimental results are analysed.

Keywords: digital image forensics; convolutional neural networks; natural images; computer generated graphics; inception-v3.

DOI: 10.1504/IJAACS.2021.114295

International Journal of Autonomous and Adaptive Communications Systems, 2021 Vol.14 No.1/2, pp.151 - 162

Received: 06 Jan 2020
Accepted: 09 Apr 2020

Published online: 07 Apr 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article