1. Study on no-reference quality assessment method of neutron radiographic images based on residual network
- Author
-
QIAO Shuang, LI Junhui, ZHAO Chenyi, and ZHANG Tian
- Subjects
neutron radiographic images ,no-reference image quality assessment ,residual network ,gradient magnitude similarity deviation ,Nuclear engineering. Atomic power ,TK9001-9401 - Abstract
BackgroundThe quality of neutron radiographic images is mainly evaluated by human visual system (HVS), but HVS cannot be used as a real-time auxiliary for optimization parameters of neutron imaging systems.PurposeThis study aims to evaluate the quality of neutron radiographic images by no-reference image quality assessment (NR-IQA) and provide an effective approach for the parameters optimization of neutron imaging systems.MethodsFirstly, the plain natural images distorted with different distortion levels and types were labelled with quality scores to construct an experimental dataset by the gradient magnitude similarity deviation (GMSD) method. Then, the residual network (ResNet) model was employed to evaluate the quality of neutron radiographic images without reference images. Finally, the goal of extracting features and assessing the quality of neutron radiographic images was achieved by training the ResNet.ResultsThe model performs well in the test set of the experimental dataset and the quality prediction of the two group authentic neutron radiographic images.ConclusionsThe proposed quality assessment method could be used for the quality prediction of neutron radiographic images.
- Published
- 2021
- Full Text
- View/download PDF