Image inpainting for ECEI based on DeepFillv2 model

Abstract

In recent years, electron cyclotron emission imaging (ECEI) diagnostics have played an increasingly important role in magnetic confinement fusion research. However, imaging diagnostics face a significant challenge characterized by the degradation of image quality due to the presence of abnormal pixels. To address this issue, a novel image inpainting method specifically for ECEI has been developed based on DeepFillv2 model. Comparing four different types of methods (Free-Form Image Inpainting with Gated Convolution (DeepFillv2), Mean Fill (MF) , Navier-Stokes Equation (NS), and Fast Forward Marching (FFM)), DeepFillv2 model is selected for its superior performance. The performance is evaluated by calculating the mean square error (MSE), peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). For J-TEXT ECEI image inpainting model, the results show that even the ratio of randomly distributed abnormal channel to total channels reaches 50 %, the SSIM between the restored image and the original image is more than 90 % and the PSNR is more than 30 dB, indicating the excellent performance. The application on J-TEXT experiment analysis also shows the model can improve the image quality and provide more useful information.