Screen-shot and Demoiréd image identification based on DenseNet and DeepViT

How to identify the screen-shot image is an important branch of image source forensics. Although the physical feature of moire patterns may be left after LCD recapture operation, this feature may also be well concealed with the development of deep learning-based techniques for demoireing operation. In this paper, to solve the forensic problem of screen-shot and demoired image operation, we select several typical demoireing algorithms to generate datasets for training and detecting demoired images. Meanwhile, we also perform the task of identifying specific demoireing algorithms. DenseNet can extract fine demoired image features because of its enhanced feature reuse and improved model performance. The re-attention mechanism is also added to our designed network to extract the image's global features and avoid the self-attention collapse problem in ViT. Therefore, we design a network based on DenseNet cascaded with DeepViT structure to detect the demoired image and identify its corresponding demoireing algorithm. In a large number of comparison experiments of various typical image recapture detection methods, our method achieves the best detection results and network performance.

Automated summary

This paper focuses on the forensic problem of screen-shot and demoired image operation. The network designed combines DenseNet and DeepViT structure, generates datasets for training and detecting demoired images by selecting typical demoireing algorithms, and adds the re-attention mechanism to extract global features of the image. The method achieves the best detection results and network performance in comparison experiments.