• Home
  • Search
  • Segmentation-based quantification of timber surface defects via improved YOLO-TDN and morphological measurement
  • https://doi.org/10.1080/17480272.2026.2615040Copy DOI Icon

Segmentation-based quantification of timber surface defects via improved YOLO-TDN and morphological measurement

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

ABSTRACT This study proposed a non-destructive, computer-vision method for segmentation and size measurement of timber surface defects. An YOLO-TimberDefectNet (YOLO-TDN) was developed and coupled the segmentation results with morphological operations to obtain calibrated dimensions. A 506-image dataset covering three defect types (cracks, decay, holes) was constructed, and model hyperparameters were optimized via orthogonal and comparative experiments. To address small targets and complex wood textures, the spatial and channel reconstruction convolution (SCConv) module and the efficient multi-scale attention (EMA) module were introduced to enhance key-feature learning and context awareness. Ablation studies confirmed improvements over the baseline, with Box precision improving from 0.752–0.802 (+5.0%), Mask precision from 0.738–0.800 (+6.2%), and mAP@0.5 from 0.633–0.667 (+3.4%). Defect parameters relevant to structural performance – crack length/width and area/perimeter of decay and holes were accurately quantified using OpenCV algorithms with camera calibration. Robustness tests under varying illumination showed hole-area errors ≤ 3% and crack-width errors < 15% (mean 4.8%). The proposed pipeline provides camera-calibrated metrology for timber components, supporting in-service assessment, durability evaluation, and maintenance planning in wood engineering.

Similar Papers
  • PDF
  • Research Article
  • Citations173

Deep Learning for Semantic Segmentation of Defects in Advanced STEM Images of Steels

  • Sep 04, 2019
  • Scientific Reports
  • Graham Roberts +5
  • Conference Article
  • Citations5

Asset Integrity Inspection with AI for Topside Offshore Structures &amp; Marine Terminals

  • Apr 24, 2023
  • Reza Zolfaghari +6
  • Conference Article

The Application of an Artificial Neural Network As a Baseline Model For Condition Monitoring of Innovative Humidified Micro Gas Turbine Cycles

  • Jun 13, 2022
  • Kathryn Colquhoun +2
  • Conference Article
  • Citations8

Camera calibration based on divided region LS-SVM

  • Aug 01, 2008
  • Sheng Liu +2
  • Research Article

DFI-Net: dual-branch feature interaction network with attention mechanism for metal workpiece surface defect segmentation

  • Feb 20, 2026
  • Measurement Science and Technology
  • Xiaojun Zheng +2
  • PDF
  • Research Article
  • Citations47

Context awareness in process monitoring of additive manufacturing using a digital twin

  • Jan 07, 2022
  • The International Journal of Advanced Manufacturing Technology
  • Raven T Reisch +6
  • Research Article
  • Citations22

Unseen-Material Few-Shot Defect Segmentation With Optimal Bilateral Feature Transport Network

  • Jul 01, 2023
  • IEEE Transactions on Industrial Informatics
  • Dexing Shan +5
  • Conference Article

Surface Defect Detection and Quantification of Mechanical Parts Based on Image Processing

  • Dec 27, 2024
  • Jieying Yang +3
  • Research Article
  • Citations10

A method of fine size measurement for telecentricity-based error compensation

  • Jul 02, 2021
  • Measurement Science and Technology
  • Wenjie Li +6
  • Research Article
  • Citations41

Intelligent Detection Algorithm Based on 2D/3D-UNet for Internal Defects of Carbon Fiber Composites

  • Jul 21, 2023
  • Nondestructive Testing and Evaluation
  • Yunze He +8
  • Research Article
  • Citations2

Prediction of cold region dew volume based on an ECOA-BiTCN-BiLSTM hybrid model.

  • Feb 04, 2025
  • Scientific reports
  • Yi Zhang +3
  • Research Article
  • Citations47

A Survey on Non-Destructive Smart Inspection of Wind Turbine Blades Based on Industry 4.0 Strategy

  • Nov 16, 2022
  • Applied Mechanics
  • Mariya Dimitrova +5
  • Research Article

A Comprehensive Deep‐Learning Framework Integrating Lesion Segmentation and Stage Classification for Enhanced Diabetic Retinopathy Diagnosis

  • Dec 28, 2025
  • International Journal of Imaging Systems and Technology
  • Ramazan İncir +1
  • PDF
  • Research Article
  • Citations9

A Pipeline Defect Instance Segmentation System Based on SparseInst

  • Nov 07, 2023
  • Sensors (Basel, Switzerland)
  • Niannian Wang +2
  • PDF
  • Research Article
  • Citations12

Segmentation of void defects in X-ray images of chip solder joints based on PCB-DeepLabV3 algorithm

  • May 24, 2024
  • Scientific Reports
  • Defeng Kong +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.