A Novel Image Inpainting Method Used for Veneer Defects Based on Region Normalization

Abstract

The quality of the veneer directly affects the quality and grade of a blockboard made of veneer. To improve the quality and utilization of a defective veneer, a novel deep generative model-based method is proposed, which can generate higher-quality inpainting results. A two-phase network is proposed to stabilize the network training process. Then, region normalization is introduced to solve the inconsistency problem between the mean and standard deviation, improve the convergence speed of the model, and prevent the model gradient from exploding. Finally, a hybrid dilated convolution module is proposed to reconstruct the missing areas of the panels, which alleviates the gridding problem by changing the dilation rate. Experiments on our dataset prove the effectiveness of the improved approach in image inpainting tasks. The results show that the PSNR of the improved method reaches 33.11 and the SSIM reaches 0.93, which are superior to other methods.

Image completion algorithm of anthurium spathes based on multi-scale feature learning

“…Traditional image completion is mainly carried out by geometric modeling, texture matching, line fitting, and other methods ( Li et al., 2013 ; Xia et al., 2013 ; Huang et al., 2014 ; Chan et al., 2015 ; Amayo et al., 2017 ; Iizuka et al., 2017 ; Li et al., 2019 ; Ge et al., 2022 ). For example, Wang et al.…”

“…Traditional image completion is mainly carried out by geometric modeling, texture matching, line fitting, and other methods (Li et al, 2013;Xia et al, 2013;Huang et al, 2014;Chan et al, 2015;Amayo et al, 2017;Iizuka et al, 2017;Li et al, 2019;Ge et al, 2022). For example, Wang et al repaired incomplete maize leaf images by detecting and matching broken points, as well as fitting the Bezier curve of broken leaves, and then completed the segmentation of corn plants (Wang et al, 2020).…”