Communications of the ACM
Discerning Deep Fakes Digitally
Credit: Getty Images
Researchers have developed a forensic method based on a convolutional neural network that can effectively distinguish between natural images and computer-generated graphics.
Min Long and Sai Long of the School of Computer and Communication Engineering at the Changsha University of Science and Technology, and Fei Peng and Xiao-hua Hu of the School of Computer Science and Electronic Engineering at Hunan University, constructed a network model fine-tuned using a database of 10,000 images.
They describe their work in "Identifying Natural Images and Computer-Generated Graphics Based on Convolutional Neural Network," published in the International Journal of Autonomous and Adaptive Communications Systems.
The proof of principle shows how well the system can distinguish between natural and artificial images.
From Tech Xplore
View Full Article
No entries found