重庆邮电大学学报（自然科学版）2025，Vol.37Issue(5)：677-687,11.DOI:10.3979/j.issn.1673-825X.202408150220
基于深度学习的木板激光散斑图像分类研究
Classification of wood board laser speckle images based on deep learning
摘要
Abstract
This study proposes a wood board recognition method that integrates laser speckle technology with deep learning.Conventional photography and laser speckle imaging were employed to capture wood board images before and after modifica-tion treatments under both normal lighting and adverse conditions(including darkness and defocusing).A corresponding dataset was then constructed.Classification experiments were conducted using the ResNet34 deep learning model.The re-sults show that the ResNet34 model achieves high recognition accuracy when classifying laser speckle datasets and maintains good performance even under adverse environmental conditions.Furthermore,by introducing a convolutional block attention module(CBAM)to optimize the ResNet34 convolutional neural network,the classification accuracy for laser speckle ima-ges reached 93.29％.The combination of laser speckle technology and deep learning provides a low-environmental-require-ment,efficient,and promising approach for wood board classification.关键词
激光散斑/ResNet34/图像分类/木板识别/深度学习Key words
laser speckle/ResNet34/image classification/wood board recognition/deep learning分类
计算机与自动化引用本文复制引用
杜艳秋,李鑫,康辉,孙辉..基于深度学习的木板激光散斑图像分类研究[J].重庆邮电大学学报（自然科学版）,2025,37(5):677-687,11.基金项目
黑龙江省自然科学基金项目(LH2023F049) （LH2023F049）
黑龙江省博士后科研启动基金项目(2023BSH02) （2023BSH02）
黑龙江省省属本科高校基本科研业务费项目(2024-KYYWF-1083)Heilongjiang Provincial Natural Science Foundation(LH2023F049) （2024-KYYWF-1083）
Heilongjiang Provincial Postdoctoral Startup Research Fund(2023BSH02) （2023BSH02）
Fundamental Research Funds for the Provincial Universities in Heilongjiang Province(2024-KYYWF-1083) （2024-KYYWF-1083）
