Deep learning methods for neutron image restoration. (August 2023)

• Record Type: Journal Article
• Authors: Yang, Jiarui; Zhao, Chenyi; Qiao, Shuang; Zhang, Tian; Yao, Xiangyu
• Is Part Of: Annals of nuclear energy. Volume 188(2023)
• Publication Date: 2023-08
• Subjects: Neutron images -- Image restoration -- Deep neural network -- Deburring; Nuclear energy -- Periodicals; Nuclear engineering -- Periodicals; 621.4805
• DOI: 10.1016/j.anucene.2023.109820
• Languages: English
• ISSNs: 0306-4549

Abstract

Highlights: A study on the use of deep learning model in the field of neutron image restoration is performed. A lightweight, convenient and efficient deep learning network is proposed for neutron image restoration. The X-ray dataset solves the problem of lack of real neutron image datasets. The pre-training model achieves good results in real neutron image restoration. Abstract: Traditional neutron image restoration (NIR) methods lack flexibility and generalization in dealing with multiple image restoration tasks, which indirectly limits the practical applications of neutron images. Deep convolutional neural networks (CNNs) have achieved impressive success in image restoration, so this paper preliminarily explores and applies deep CNNs in NIR. Considering the characteristics and applications of neutron images, we propose a fast and lightweight densely connected attention U-Net (DAUNet) for NIR. We strengthen the network's attention to the image structural information and the processing at different frequencies by adding an attention mechanism to the symmetric skip connection under each scale of U-Net. The proposed DAUNet uses a single model for recovering images with different degradations, such as additive noise and blur. Extensive experiments on synthetic and real neutron-degraded images are conducted, and the results show that DAUNet is effective and efficient in NIR and achieves satisfactory results in terms of both comprehensive performance (PSNR) and intrinsic metrics (parameters, memory cost and running time), which are highly attractive for practical applications. In addition, to address the problem of lacking real NIR datasets, we use X-ray images that the imaging principles are closer to that of neutron imaging as data drivers for the network.