森林工程2024，Vol.40Issue(1)：98-105,8.DOI:10.3969/j.issn.1006-8023.2024.01.011
基于匹配语义感知的单板缺陷图像修复研究
Image Inpainting Research of Veneer Defect Based on Match Attention
摘要
Abstract
The quality of veneer determines the grade of veneer wood-based panels and the treatment of defects on veneer becomes an important part of wood processing.In order to deal with veneer defects and improve wood utilization,an image inpainting method of venerr defect based on match attention is proposed.The method proposes a match attention module to acquire features at a distance to enhance the accuracy of the model and uses a double convolution module that captures multi-scale contextual information.Then region normalization is used throughout the network to avoid mean and variance bias.Peak signal-to-noise ratio(PSNR)and structural simi-larity index(SSIM)are used as evaluation indicators.The results show that the PSNR of the improved method reaches 28.48,and the SSIM reaches 0.91.Compared to the globally and locally consistent image completion(GL)method,the PSNR and SSIM are im-proved by 1.03% and 0.05%,respectively.This method can achieve consistent effect in structure and texture,which providing guid-ance for the inpainting of the veneer defects.关键词
图像修复/深度学习/单板缺陷/匹配语义感知/区域归一化Key words
Image inpainting/deep learning/veneer defect/match attention/region normalization分类
农业科技引用本文复制引用
葛奕麟,孙丽萍,王頔..基于匹配语义感知的单板缺陷图像修复研究[J].森林工程,2024,40(1):98-105,8.基金项目
中央高校基础研究基金(2572019BF08). （2572019BF08）
