Radial Based Analysis of GRNN in Non-Textured Image Inpainting
This work addresses image restoration for damaged non-textured images, but it appears incremental as it modifies an existing method (GRNN) with radial analysis.
The paper tackled image inpainting for non-textured images by applying radial-based analysis to GRNN, achieving improved outcomes as measured by PSNR values in comparative tests with algorithms like LS-SVM.
Image inpainting algorithms are used to restore some damaged or missing information region of an image based on the surrounding information. The method proposed in this paper applies the radial based analysis of image inpainting on GRNN. The damaged areas are first isolated from rest of the areas and then arranged by their size and then inpainted using GRNN. The training of the neural network is done using different radii to achieve a better outcome. A comparative analysis is done for different regression-based algorithms. The overall results are compared with the results achieved by the other algorithms as LS-SVM with reference to the PSNR value.