Optical detection of beetle-related indicators and stem quality in roundwood using convolutional neural networks

Abstract Accurate roundwood sorting is critical for improving resource efficiency in the timber industry. However, in many small sawmills, sorting is performed manually through visual inspection, often resulting in inconsistencies and misclassifications. Sorting wood based on macroscopic images usin...

Full description

Saved in:
Bibliographic Details
Main Authors: Julia Achatz, Mark Schubert
Format: Article
Language:English
Published: SpringerOpen 2025-05-01
Series:Journal of Wood Science
Subjects:
Online Access:https://doi.org/10.1186/s10086-025-02197-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850270902388785152
author Julia Achatz
Mark Schubert
author_facet Julia Achatz
Mark Schubert
author_sort Julia Achatz
collection DOAJ
description Abstract Accurate roundwood sorting is critical for improving resource efficiency in the timber industry. However, in many small sawmills, sorting is performed manually through visual inspection, often resulting in inconsistencies and misclassifications. Sorting wood based on macroscopic images using convolutional neural networks (CNN) is a cost-effective and efficient approach. However, current models focus primarily on cross-sectional images, limiting their ability to detect important features like knots and beetle infestations. We present an industrial dataset of 5,200 samples, each including both a trunk and a cross-sectional image. Using this dataset, we developed two models: a stem quality classification model and a beetle-indicator detection model. The first model uses only trunk images to extract stem information, supporting existing cross-sectional models. The beetle-indicator detection model utilizes both trunk and cross-sectional images, introducing a new detection capability to computer vision-based roundwood sorting. To ensure transparency and interpretability, we applied Explainable Artificial Intelligence (XAI) techniques to highlight key regions within the images that influenced the models’ predictions. The stem quality model achieves 80% accuracy in trunk feature analysis, and the beetle-indicator model reaches 89% accuracy. Together, these models improve automation based on convolutional neural networks by enabling detailed trunk analysis and early beetle infestation detection.
format Article
id doaj-art-ef41d36f93f04ee188a722ee74b68b94
institution OA Journals
issn 1611-4663
language English
publishDate 2025-05-01
publisher SpringerOpen
record_format Article
series Journal of Wood Science
spelling doaj-art-ef41d36f93f04ee188a722ee74b68b942025-08-20T01:52:24ZengSpringerOpenJournal of Wood Science1611-46632025-05-0171111310.1186/s10086-025-02197-xOptical detection of beetle-related indicators and stem quality in roundwood using convolutional neural networksJulia Achatz0Mark Schubert1Cellulose and Wood Materials, Group WoodTec, Empa Material Science and TechnologyCellulose and Wood Materials, Group WoodTec, Empa Material Science and TechnologyAbstract Accurate roundwood sorting is critical for improving resource efficiency in the timber industry. However, in many small sawmills, sorting is performed manually through visual inspection, often resulting in inconsistencies and misclassifications. Sorting wood based on macroscopic images using convolutional neural networks (CNN) is a cost-effective and efficient approach. However, current models focus primarily on cross-sectional images, limiting their ability to detect important features like knots and beetle infestations. We present an industrial dataset of 5,200 samples, each including both a trunk and a cross-sectional image. Using this dataset, we developed two models: a stem quality classification model and a beetle-indicator detection model. The first model uses only trunk images to extract stem information, supporting existing cross-sectional models. The beetle-indicator detection model utilizes both trunk and cross-sectional images, introducing a new detection capability to computer vision-based roundwood sorting. To ensure transparency and interpretability, we applied Explainable Artificial Intelligence (XAI) techniques to highlight key regions within the images that influenced the models’ predictions. The stem quality model achieves 80% accuracy in trunk feature analysis, and the beetle-indicator model reaches 89% accuracy. Together, these models improve automation based on convolutional neural networks by enabling detailed trunk analysis and early beetle infestation detection.https://doi.org/10.1186/s10086-025-02197-xRoundwood sortingTrunk datasetArtificial intelligenceConvolutional neural networkBeetle wood indicator detection
spellingShingle Julia Achatz
Mark Schubert
Optical detection of beetle-related indicators and stem quality in roundwood using convolutional neural networks
Journal of Wood Science
Roundwood sorting
Trunk dataset
Artificial intelligence
Convolutional neural network
Beetle wood indicator detection
title Optical detection of beetle-related indicators and stem quality in roundwood using convolutional neural networks
title_full Optical detection of beetle-related indicators and stem quality in roundwood using convolutional neural networks
title_fullStr Optical detection of beetle-related indicators and stem quality in roundwood using convolutional neural networks
title_full_unstemmed Optical detection of beetle-related indicators and stem quality in roundwood using convolutional neural networks
title_short Optical detection of beetle-related indicators and stem quality in roundwood using convolutional neural networks
title_sort optical detection of beetle related indicators and stem quality in roundwood using convolutional neural networks
topic Roundwood sorting
Trunk dataset
Artificial intelligence
Convolutional neural network
Beetle wood indicator detection
url https://doi.org/10.1186/s10086-025-02197-x
work_keys_str_mv AT juliaachatz opticaldetectionofbeetlerelatedindicatorsandstemqualityinroundwoodusingconvolutionalneuralnetworks
AT markschubert opticaldetectionofbeetlerelatedindicatorsandstemqualityinroundwoodusingconvolutionalneuralnetworks